Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks Ahmad Rashid, Serena Hacker, Guojun Zhang, Agustinus Kristiadi and Pascal Poupart
International Conference on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain, 2024.
[paper.pdf]
[code]
Calibrated One Round Federated Learning with Bayesian Inference in the
Predictive Space Mohsin Hasan, Guojun Zhang, Kaiyang Guo, Xi Chen, Pascal Poupart
International Conference of the Association for the Advancement of Artificial Intelligence (AAAI), Vancouver, BC, 2024.
[paper.pdf]
[code]
2023
Batchnorm Allows Unsupervised Radial Attacks Amur Ghose, Apurv Gupta, Yaoliang Yu and Pascal Poupart
Advances in Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023.
[paper.pdf]
[code]
An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient Yudong Luo, Guiliang Liu, Pascal Poupart and Yangchen Pan
Advances in Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023.
[paper.pdf] [code]
Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations Guanren Qiao, Guiliang Liu, Pascal Poupart and Zhiqiang Xu
Advances in Neural Information Processing Systems (NeurIPS), New Orleans, USA, 2023.
[paper.pdf] [supplementary material] [code]
Contrastive Deterministic Autoencoders For Language Modeling Amur Ghose and Pascal Poupart
Findings of the International Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), Singapore, 2023.
[paper.pdf] [code]
Attribute Controlled Dialogue Prompting Runcheng Liu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh and Pascal Poupart
Findings of the Annual Meeting of the Association for Computational Linguistics (ACL-findings), Toronto, Canada, 2023.
[paper.pdf]
Do we need Label Regularization to Fine-tune Pretrained Language Models? Ivan Kobyzev, Aref Jafari, Mehdi Rezagholizadeh, Tianda Li, Alan Do-Omri, Peng Lu, Pascal Poupart and Ali Ghodsi
Conference of the European Chapter of the Association for Computational Linguistics (EACL), Dubrovnik, Croatia, 2023.
[paper.pdf]
Benchmarking Constraint Inference in Inverse Reinforcement Learning Guiliang Liu, Yudong Luo, Ashish Gaurav, Kasra Rezaee, Pascal Poupart
International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023.
[paper.pdf][code]
Learning Soft Constraints from Constrained Expert Demonstrations Ashish Gaurav, Kasra Rezaee, Guiliang Liu, Pascal Poupart
International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023.
[paper.pdf][code]
NTS-NOTEARS: Learning Non-parametric DBNs with Prior Knowledge Xiangyu Sun, Oliver Schulte, Guiliang Liu, Pascal Poupart
International Conference on Artificial Intelligence and Statistics (AISTATS), Valencia, Spain, 2023.
[paper.pdf][code]
FedFormer: Contextual Federation with Attention in Reinforcement Learning Liam Hebert, Lukasz Golab, Pascal Poupart, Robin Cohen
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), London, UK, 2023.
[paper.pdf][code]
2022
Uncertainty-Aware Reinforcement Learning for Risk-Sensitive Player Evaluation in Sports Game Guiliang Liu, Yudong Luo, Oliver Schulte, Pascal Poupart
Advances in Neural Information Processing Systems (NeurIPS), New Orleans, 2022.
[paper.pdf][code and supplemental]
Continuation KD: Improved Knowledge Distillation Through the lens of Continuation Optimization Aref Jafari, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart and Ali Ghodsi
Findings of the International Conference on Empirical Methods in Natural Language Processing (EMNLP-Findings), pages 5260–5269, Abu Dhabi, 2022.
[paper.pdf]
Optimality and stability in non-convex smooth games Guojun Zhang, Pascal Poupart, Yaoliang Yu
Journal of Machine Learning Research (JMLR), 23(135):1-71, 2022.
[link]
Learning Functions on Multiple Sets using Multi-Set Transformers Kira A. Selby, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart
International Conference on Uncertainty in Artificial Intelligence (UAI), Eindhoven, Netherlands, 2022.
[paper.pdf][code]
Linearizing Contextual Bandits with Latent State Dynamics Elliot Nelson, Debarun Bhattacharjya, Tian Gao, Miao Liu, Djallel Bouneffouf, Pascal Poupart
International Conference on Uncertainty in Artificial Intelligence (UAI), Eindhoven, Netherlands, 2022.
[paper.pdf][supplementary.zip]
CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation Md Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar, Khalil Bibi, Philippe Langlais and Pascal Poupart
International Conference on Computational Linguistics (COLING), pages 4707–4713, Gyeongju, Republic of Korea, 2022.
[paper.pdf]
RAIL-KD: Random Intermediate Layer Mapping for Knowledge Distillation Md Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh, Abbas Ghaddar, Philippe Langlais, Pascal Poupart
Findings of the Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL Findings), Seattle, USA, 2022.
[paper.pdf]
WatClaimCheck: A New Dataset for Claim Entailment and Inference Kashif Khan, Ruizhe Wang, Pascal Poupart
Annual Meeting of the Association for Computational Linguistics (ACL), Dublin, Ireland, 2022.
[paper.pdf][code and dataset]
Learning Object-Oriented Dynamics for Planning from Text Guiliang Liu, Ashutosh Adhikari, Amir-Massoud Farahmand, Pascal Poupart
International Conference on Learning Representations (ICLR), Virtual conference, 2022.
[paper.pdf][supplementary.zip][code]
Distributional Reinforcement Learning with Monotonic Splines Yudong Luo, Guiliang Liu, Haonan Duan, Oliver Schulte, Pascal Poupart
International Conference on Learning Representations (ICLR), Virtual conference, 2022.
[paper.pdf][code]
Decentralized Mean Field Games Sriram Ganapathi, Matthew Taylor, Mark Crowley, Pascal Poupart
International Conference of the Association for the Advancement of Artificial Intelligence (AAAI), Virtual conference, 2022.
[paper.pdf][code]
2021
Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning Guiliang Liu, Xiangyu Sun, Oliver Schulte, Pascal Poupart
Advances in Neural Information Processing Systems (NeurIPS), Virtual conference, 2021.
[paper.pdf][supplementary.pdf][code]
Quantifying and Improving Transferability in Domain Generalization Guojun Zhang, Han Zhao, Yaoliang Yu, Pascal Poupart
Advances in Neural Information Processing Systems (NeurIPS), Virtual conference, 2021.
[paper.pdf][supplementary.pdf][code]
Prediction by Anticipation: An Action-Conditional Prediction Method Based on Interaction Learning Ershad Banijamali, Mohsen Rohani, Elmira Amirloo, Jun Luo, Pascal Poupart
IIEEE/CVF International Conference on Computer Vision (ICCV), Virtual conference, pp. 15621-15630, 2021.
[paper.pdf][supplementary.pdf]
Self-supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map Elmira Amirloo Abolfathi, Mohsen Rohani, Ershad Banijamali, Jun Luo, Pascal Poupart
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Virtual conference, pp. 8494-8503, 2021.
[paper.pdf]
Partially Observable Mean Field Reinforcement Learning Sriram Ganapathi Subramanian, Matthew Taylor, Mark Crowley, Pascal Poupart
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Virtual conference, 2021.
[paper.pdf][code]
2020
Learning Dynamic Belief Graphs to Generalize on Text-Based Games Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Cote, Mikulas Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William Hamilton,
Advances in Neural Information Processing Systems (NeurIPS), Virtual conference, 2020.
[paper.pdf] [supplementary.pdf] [code]
Learning Agent Representations for Ice Hockey Guiliang Liu, Oliver Schulte, Pascal Poupart, Mike Rudd, Mehrsan Javan,
Advances in Neural Information Processing Systems (NeurIPS), Virtual conference, 2020.
[paper.pdf] [supplementary.pdf] [code]
Online Bayesian Moment Matching based SAT Solver Heuristics Haonan Duan, Saeed Nejati, George Trimponias, Pascal Poupart and Vijay Ganesh
International Conference on Machine Learning (ICML), virtual conference, 2020.
[paper.pdf][supplementary.pdf][code]
Batchnorm with entropic regularization turns deterministic autoencoders into generative models Amur Ghose, Abdullah Rashwan and Pascal Poupart
International Conference on Uncertainty in Artificial Intelligence (UAI), virtual conference, 2020.
[paper.pdf][supplementary.pdf]
Inverse Reinforcement Learning for Team Sports: Valuing Actions and Players Yudong Luo, Oliver Schulte and Pascal Poupart
International Joint Conference on Artificial Intelligence (IJCAI), virtual conference, 2020.
[paper.pdf][code]
Unsupervised multilingual alignment using Wasserstein barycenter Xin Lian, Kshitij Jain, Jakub Truszkowski, Pascal Poupart and Yaoliang Yu
International Joint Conference on Artificial Intelligence (IJCAI), virtual conference, 2020.
[paper.pdf]
Multi Type Mean Field Reinforcement Learning Sriram Ganapathi Subramanian, Pascal Poupart, Matthew Taylor and Nidhi Hegde
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), virtual conference, 2020.
[paper.pdf][code]
Progressive Memory Banks for Incremental Domain Adaptation Nabiha Asghar, Lili Mou, Kira A. Selby, Kevin D. Pantasdo, Pascal Poupart and Xin Jiang
International Conference on Learning Representations (ICLR), virtual conference, 2020.
[paper.pdf][code]
Diachronic Embedding for Temporal Knowledge Graph Completion Rishab Goel, Seyed Mehran Kazemi, Marcus Brubaker and Pascal Poupart
International Conference of the Association for the Advancement of Artificial Intelligence (AAAI), New York, USA, 2020.
[paper.pdf][code]
Representation Learning for Dynamic (Knowledge) Graphs: A Survey Seyed Mehran Kazemi, Rishab Goel, Kshitij Jain, Ivan Kobyzev, Akshay Sethi, Peter Forsyth and Pascal Poupart
Journal of Machine Learning Research (JMLR), 21(70):1-73, 2020.
[link]
Learning directed acyclic graph SPNs in sub-quadratic time Amur Ghose, Priyank Jaini and Pascal Poupart
International Journal of Approximate Reasoning (IJAR), volume 120, pages 48-73, 2020.
[link]
Discriminative Training of Feed-Forward and Recurrent Sum-Product Networks by Extended Baum-Welch Haonan Duan, Abdullah Rashwan, Pascal Poupart and Zhitang Chen
International Journal of Approximate Reasoning (IJAR) [paper.pdf]
2019
Comparing EM with GD in Mixture Models of Two Components Guojun Zhang, Pascal Poupart and George Trimponias,
International Conference on Uncertainty in Artificial Intelligence (UAI), Tel Aviv, Israel, 2019.
[paper.pdf] [supplementary.pdf] [code]
On the relationship between satisfiability and Markov decision processes Ricardo Salmon and Pascal Poupart,
International Conference on Uncertainty in Artificial Intelligence (UAI), Tel Aviv, Israel, 2019.
[paper.pdf] [supplementary.pdf] [code]
Why do neural dialog systems generate short and meaningless replies? A comparison between dialog and translation Bolin Wei, Shuai Lu, Lili Mou, Hao Zhou, Pascal Poupart, Ge Li, and Zhi Jin,
International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brighton, UK, 2019.
[paper.pdf]
2018
Unsupervised Video Object Segmentation for Deep Reinforcement Learning Vikash Goel, Jameson Weng and Pascal Poupart,
Advances in Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2018.
[paper.pdf] [supplementary.pdf] [poster.pdf] [video] [code]
Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks Agastya Kalra, Abdullah Rashwan, Wilson Hsu, Pascal Poupart, Prashant Doshi, George Trimponias,
Advances in Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2018.
[paper.pdf] [supplementary.pdf] [poster.pdf] [video] [code]
Deep Homogeneous Mixture Models: Representation, Separation and Approximation Priyank Jaini, Pascal Poupart, Yaoliang Yu,
Advances in Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2018.
[paper.pdf] [supplementary.pdf]
Monte-Carlo Tree Search for Constrained POMDPs Jongmin Lee, Geon-Hyeong Kim, Pascal Poupart, Kee-Eung Kim,
Advances in Neural Information Processing Systems (NeurIPS), Montreal, Canada, 2018.
[paper.pdf][supplementary.zip]
Variational Attention for Sequence-to-Sequence Models Hareesh Bahuleyan, Lili Mou, Olga Vechtomova and Pascal Poupart,
International Conference on Computational Linguistics (COLING), 11 pages, Santa Fe, New Mexico, USA, 2018.
[paper.pdf]
Faster Policy Adaptation in Environments with Exogeneity: A State Augmentation Approach Zhuoshu Li, Zhitang Chen, Pascal Poupart, Sanmay Das, Yanhui Geng,
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1035-1043, Stockholm, Sweden, 2018.
[paper.pdf]
Affective Neural Response Generation Nabiha Asghar, Pascal Poupart, Jesse Hoey, Xin Jiang, Lili Mou,
European Conference in Information Retrieval (ECIR), pages 154-166, Grenoble, France, 2018.
[paper.pdf]
Order-Planning Neural Text Generation from Structured Data Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, Zhifang Sui,
Association for the Advancement of Artificial Intelligence (AAAI), 8 pages, New Orleans, Louisiana, 2018.
[paper.pdf]
Discriminative Training of Sum-Product Networks by Extended Baum-Welch Abdullah Rashwan, Pascal Poupart and Zhitang Chen,
Proceedings of Machine Learning Research - International Conference on Probabilistic Graphical Models (PGM), Vol. 72, pages 356-367, Prague, Czech Republic, 2018.
[link]
Prometheus: Directly Learning Acyclic Directed Graph Structures for Sum-Product Networks Priyank Jaini, Amur Ghose and Pascal Poupart,
Proceedings of Machine Learning Research - International Conference on Probabilistic Graphical Models (PGM), Vol. 72, pages 181-192, Prague, Czech Republic, 2018.
[link]
An Empirical Study of Methods for SPN Learning and Inference Cory Butz, Jonathan Oliveira, Andreas dos Santos, Andre Teixeira, Pascal Poupart and Agastya Kalra,
Proceedings of Machine Learning Research - International Conference on Probabilistic Graphical Models (PGM), Vol. 72, pages 49-60, Prague, Czech Republic, 2018.
[link]
2017
Deep Active Learning for Dialogue Generation Nabiha Asghar, Pascal Poupart, Xin Jiang and Hang Li
Joint Conference on Lexical and Computational Semantics (*SEM), 6 pages, Vancouver, BC, Canada, 2017.
[paper.pdf]
An Empirical Study of Branching Heuristics through the Lens of Global Learning Rate Jia Hui Liang, Hari Govind, Vijay Ganesh, Pascal Poupart, Krzysztof Czarnecki
International Conference on Theory and applications of Satisfiability Testing (SAT), 16 pages, Melbourne, Australia, 2017. (runner up best student paper award)
[link]
A Propagation Rate based Splitting Heuristic form Divide-and-Conquer Solvers Saeed Nejati, Zack Newsham, Joseph Scott, Jia Hui Liang, Catherine Gebotys, Pascal Poupart and Vijay Ganesh
International Conference on Theory and applications of Satisfiability Testing (SAT), 10 pages, Melbourne, Australia, 2017.
[link]
Constrained Bayesian Reinforcement Learning via Approximate Linear Programming Jongmin Lee, Youngsoo Jang, Pascal Poupart, Kee-Eung Kim,
International Joint Conferences on Artificial Intelligence (IJCAI), 8 pages, Sydney, Australia, 2017.
[paper.pdf]
Online Bayesian Transfer Learning for Sequential Data Modeling Priyank Jaini, Zhitang Chen, Pablo Carbajal, Edith Law, Laura Middleton, Kayla Regan, Mike Schaekermann, George Trimponias, James Tung, Pascal Poupart
International Conference on Learning Representations (ICLR), 20 pages, Toulon, France, 2017.
[paper.pdf]
Online structure learning for sum-product networks with Gaussian leaves Wilson Hsu, Agastya Kalra, Pascal Poupart
International Conference on Learning Representations (ICLR) - workshop track, 16 pages, Toulon, France, 2017.
[paper.pdf][code]
Generative Mixture of Networks Ershad Banijamali, Ali Ghodsi and Pascal Poupart
International Joint Conference on Neural Networks (IJCNN), 8 pages, Anchorage, Alaska, USA, 2017.
[paper.pdf]
Discovering Conversational Dependencies between Messages in Dialogs Wenchao Du, Pascal Poupart, Wei Xu
AAAI Student Abstract, 2 pages, San Francisco, CA, USA, 2017.
[paper.pdf]
2016
A Unified Approach for Learning the Parameters of Sum-Product Networks Han Zhao, Pascal Poupart and Geoff Gordon
Advances in Neural Information Processing Systems (NIPS), 9 pages, Barcelona, Spain, 2016.
[paper.pdf][supplement]
Online Bayesian Moment Matching for Topic Modeling with Unknown Number of Topics Wei-Shou Hsu and Pascal Poupart
Advances in Neural Information Processing Systems (NIPS), 9 pages, Barcelona, Spain, 2016.
[paper.pdf][supplement][code]
Dynamic Sum-Product Networks for Tractable Inference on Sequence Data Mazen Melibari, Pascal Poupart, Prashant Doshi, George Trimponias
International Conference on Probabilistic Graphical Models (PGM), 12 pages, Lugano, Switzerland, 2016.
[paper.pdf]
Online Algorithms for Sum-Product Networks with Continuous Variables Priyank Jaini, Abdullah Rashwan, Han Zhao, Yue Liu, Ershad Banijamali, Zhitang Chen and Pascal Poupart
International Conference on Probabilistic Graphical Models (PGM), 12 pages, Lugano, Switzerland, 2016.
[paper.pdf][code]
Sum-Product-Max Networks for Tractable Decision Making Mazen Melibari, Pascal Poupart and Prashant Doshi
International Joint Conference on Artificial Intelligence (IJCAI), 7 pages, New York, USA, 2016.
[paper.pdf]
Learning Rate Based Branching Heuristic for SAT Solvers Jia Hui Liang, Vijay Ganesh, Pascal Poupart and Krzysztof Czarnecki
International Conference on Theory and Applications of Satisfiability Testing (SAT), 17 pages, Bordeaux, France, 2016.
[paper.pdf]
Online Relative Entropy Policy Search using Reproducing Kernel Hilbert Space Embeddings Zhitang Chen, Pascal Poupart and Yanhui Geng
International Conference on Artificial Intelligence and Statistics (AISTATS), 9 pages, Cadiz, Spain, 2016.
[paper.pdf]
Online and Distributed Bayesian Moment Matching for SPNs Abdullah Rashwan, Han Zhao and Pascal Poupart
International Conference on Artificial Intelligence and Statistics (AISTATS), 9 pages, Cadiz, Spain, 2016.
[paper.pdf]
Exponential Recency Weighted Average Branching Heuristic for SAT Solvers Jia Hui Liang, Vijay Ganesh, Pascal Poupart and Krysztof Czarnecki
Association for the Advancement of Artificial Intelligence (AAAI), 7 pages, Phoenix, Arizona, 2016.
[paper.pdf]
2015
On the Relationship Between Sum-Product Networks and Bayesian Networks Han Zhao, Mazen Melibari, Pascal Poupart
International Conference on Machine Learning (ICML), 9 pages, Lille, France, 2015.
[paper.pdf][supplement][longer
arXiv version]
Self-Adaptive Hierarchical Sentence Model Han Zhao, Zhengdong Lu and Pascal Poupart,
International Joint Conference on Artificial Intelligence (IJCAI), 8 pages, Buenos Aires, Argentina, 2015.
[paper.pdf]
Incremental Policy Iteration with Guaranteed Escape from Local Optima in POMDP Planning Marek Grzes and Pascal Poupart
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 9 pages, Istanbul, Turkey, 2015.
[paper.pdf]
Energy Efficient Execution of POMDP Policies Marek Grzes, Pascal Poupart, Xiao Yang and Jesse Hoey
IEEE Transactions on Systems Man and Cybernetics, Volume
45, Issue 11, pages 2484-2497, 2015.
[link]
SoF: Soft-Cluster Matrix Factorization for Probabilistic Clustering Han Zhao, Pascal Poupart, Yongfeng Zhang and Martin Lysy
Association for the Advancement of Artificial Intelligence (AAAI), 8 pages, Austin, Texas, USA, 2015.
[paper.pdf]
Approximate Linear Programming for Constrained Partially Observable Markov Decision Processes Pascal Poupart, Aarti Malhotra, Pei Pei, Kee-Eung Kim, Bongseok Goh and Michael Bowling
Association for the Advancement of Artificial Intelligence (AAAI), 7 pages, Austin, Texas, USA, 2015.
[paper.pdf]
2014
POMDP Planning and Execution in an Augmented Space Marek Grzes and Pascal Poupart
International Conference on Autonomous Agents and Multiagent
Systems (AAMAS), 8 pages, Paris, France, 2014.
[paper.pdf]
POMDP Planning by Marginal-MAP Probabilistic Inference in Generative Models Igor Kiselev and Pascal Poupart
AAMAS Workshop on Adaptive Learning Agents, 8 pages,
Paris, France, 2014.
[workshop paper][extended abstract]
A Sober Look at Spectral Learning Han Zhao and Pascal Poupart
ICML Workshop on the Method of Moments and Spectral Learning, 5 pages, Beijing, China, 2014.
[paper.pdf][code]
Upper Limb Contributions to Frontal Plane Balance Control
in Rollator-Assisted Walking James Y Tung, William H Gage, Pascal Poupart and William E McIlroy
Assistive Technology, Volume 26, Issue 1, pages 15-21, 2014.
[link]
Measuring life space in older adults with mild-to-moderate Alzheimer's disease using mobile phone GPS James Y Tung, Rhiannon V. Rose, Emnet Gammada, Isabel Lam, Eric A. Roy, Sandra E. Black, Pascal Poupart
Gerontology, Volume 60, Issue 2, pages 154-162, 2014.
[link]
Transparent Muscle Characterization Using Quantitative Electromyography: Different Binarization Mappings Meena Abdel Maseeh, T. Chen, Pascal Poupart, Ben Smith, Daniel Stashuk
IEEE Transactions on Neural Systems and Rehabilitation
Engineering, Volume 22, Issue 3, pages 511-521, 2014.
[link]
2013
Controller Compilation and Compression for Resource Constrained Applications Marek Grzes, Pascal Poupart and Jesse Hoey
Algorithmic Decision Theory (ADT), 15 pages, Brussels, Belgium, 2013.
[paper.pdf]
Isomorph-free Branch and Bound Search for Finite State Controllers Marek Grzes, Pascal Poupart and Jesse Hoey
International Joint Conferences on Artificial Intelligence (IJCAI), 7 pages, Beijing, China, 2013.
[paper.pdf]
Learning Community-based Preferences via Dirichlet Process Mixtures of Gaussian Processes
Ehsan Abbasnejad, Scott Sanner, Edwin V Bonilla and Pascal Poupart
International Joint Conferences on Artificial Intelligence (IJCAI), 7 pages, Beijing, China, 2013.
[paper.pdf][code]
Iterative Model Refinement of Recommender MDPs based on Expert Feedback Omar Zia Khan, Pascal Poupart and John Mark Agosta
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECMLPKDD), 16 pages, Prague, Czech Republic, 2013.
[paper.pdf]
2012
People, Sensors, Decisions: Customizable and Adaptive Technologies for Assistance in Healthcare Jesse Hoey, Craig Boutilier, Pascal Poupart, Patrick Olivier, Andrew Monk and Alex Mihailidis
ACM Transactions on Interactive Intelligent Systems, Volume 2, Issue 4, 36 pages, 2012.
[link]
Bayesian Reinforcement Learning Nikos Vlassis, Mohammad Ghavamzadeh, Shie Mannor and Pascal Poupart
Reinforcement Learning: State-of-the-Art, Springer Verlag, Editors: Marco Wieiring and Martijn van Otterlo, pages 359-386, 2012.
[link]
Symbolic Dynamic Programming for Continuous State and Observation POMDPs Zhara Zamani, Scott Sanner, Pascal Poupart and Kristian Kersting
Neural Information Processing Systems (NIPS), Lake Tahoe, NV, 2012.
[paper.pdf]
Cost-Sensitive Exploration in Bayesian Reinforcement Learning Dongho Kim, Kee-Eung Kim and Pascal Poupart
Neural Information Processing Systems (NIPS), Lake Tahoe, NV, 2012.
[paper.pdf]
Hierarchical Double Dirichlet Process Mixture of Gaussian Processes Adita Tayal, Pascal Poupart and Yuying Li
National Conference on Artificial Intelligence (AAAI), Toronto, ON, 2012.
[paper.pdf]
Muscle Categorization using Quantitative Needle Electromiography: A Two Stage Gaussian Mixture Model based Approach Meena Abdel Maseeh, Pascal Poupart, Benn Smith, Daniel Stashuk
International Conference on Machine Learning Applications (ICMLA), Boca Raton, FL, 2012.
[paper.pdf]
2011
An Introduction to Fully and Partially Observable Markov Decision Processes Pascal Poupart
Chapter 3 in Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions, Eds. Enrique Sucar, Eduardo Morales and
Jesse Hoey, IGI Global, pages 33-62, 2011.
[link to book]
POMDP Models for Assistive Technology Jesse Hoey, Pascal Poupart, Craig Boutilier and Alex Mihailidis
Chapter 13 in Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions, Eds. Enrique Sucar, Eduardo Morales and Jesse Hoey, IGI Global, pages 294-314, 2011.
[link to book]
Automatically Generated Explanations for Markov Decision Processes Omar Zia Khan, Pascal Poupart and James Black
Chapter 7 in Decision Theory Models for Applications in Artificial Intelligence: Concepts and Solutions, Eds. Enrique Sucar, Eduardo Morales and
Jesse Hoey, IGI Global, pages 144-163, 2011.
[link to book]
Automated Explanations for MDP Policies Omar Zia Khan, Pascal Poupart and James Black
NIPS Workshop on Decision Making with Multiple Imperfect Decision Makers, Sierra Nevada, Spain, 2011.
[paper.pdf] (NB: This is a short paper that summarizes our ICAPS 2009 paper as well as the book chapter above)
Exploiting Structure in Weighted Model Counting Approaches to Probabilistic Inference Wei Li, Pascal Poupart and Peter van Beek
Journal of Artificial Intelligence Research (JAIR), Volume 40, pages 729-765, 2011.
[paper.pdf]
Automated Refinement of Bayes Networks' Parameters based on Test Ordering Constraints Omar Zian Khan, Pascal Poupart and John Mark Agosta
Advances in Neural Information Processing Systems (NIPS), Grenada, Spain, 2011.
[paper.pdf]
Point-based Value Iteration for Constrained POMDPs Dongho Kim, Jaesong Lee, Kee-Eung Kim and Pascal Poupart
International Joint Conference on Artificial Intelligence (IJCAI), Barcelona, Spain, 2011.
[paper.pdf]
Continuous Correlated Beta Processes Robby Goetschalckx, Pascal Poupart and Jesse Hoey
International Joint Conference on Artificial Intelligence (IJCAI), Barcelona, Spain, 2011.
[paper.pdf]
Analyzing and Escaping Local Optima in Planning as Inference for Partially Observable Domains Pascal Poupart, Tobias Lang and Marc Toussaint
European Conference on Machine Learning (ECML), Athens, Greece, 2011.
[paper.pdf]
Escaping Local Optima in POMDP Planning as Inference Pascal Poupart, Tobias Lang and Marc Toussaint
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Taipei, Taiwan, 2011.
[extended-abstract.pdf] (NB: this is an extended abstract of the ECML paper above)
Smart Walkers! Enhancing the Mobility of the Elderly Mathieu Sinn and Pascal Poupart
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Taipei, Taiwan, 2011.
[extended-abstract.pdf]
Error Bounds for Online Predictions of Linear-Chain Conditional Random Fields: Application to Activity Recognition for Users of Rolling Walkers Mathieu Sinn and Pascal Poupart
IEEE International Conference on Machine Learning and Applications (ICMLA), Honolulu, Haiwai, 2011.
[link to paper]
Closing the Gap: Improved Bounds on Optimal POMDP Solutions Pascal Poupart, Kee-Eung Kim and Dongho Kim
International Conference on Automated Planning and Scheduling (ICAPS), Freiburg, Germany, 2011.
[paper.pdf][software]
3D Pose Tracking of Walker Users' Lower Limb with a Structured Light Camera on a Moving Platform Richard Hu, Adam Hartfiel, James Tung, Adel Fakih, Jesse Hoey and Pascal Poupart
Workshop on Human Activity Understanding from 3D Data (HAU3D) at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, 2011.
[paper.pdf]
Asymptotic Theory for Linear-Chain Conditional Random Fields Mathieu Sinn and Pascal Poupart
International Conference on Artificial Intelligence and Statistics (AISTATS), Fort Lauderdale, FL, 2011
[paper.pdf][supplementary
material]
A Bayesian Approach to Online Performance Modeling for Database Appliances using Gaussian Models Muhammad Bilal Sheikh, Umar Farooq Minhas, Omar Zia Khan, Ashraf Aboulnaga, Pascal Poupart and David J. Taylor
IEEE/ACM International Conference on Autonomic Computing (ICAC), Karlsruhe, Germany, 2011.
[paper.pdf]
VALMA: Voice, Activity and Location Monitoring for Alzheimer's Disease and Related Dementias James Y. Tung, Jonathan F.L. Semple, Wei Xian Woo, Wei-Shou Hsu, Mathieu Sinn, Eric A. Roy and Pascal Poupart
Annual Conference of the Rehabilitation Engineering and Assistive Technology Society of North America (RESNA), Toronto, ON, 2011.
[paper.pdf]
Ambulatory Assessment of Lifestyle Factors for Alzheimer's Disease and Related Dementias James Y. Tung, Jonathan F. Semple, Wei Xian Woo, Wei-Shou Hsu, Mathieu Sinn, Eric A. Roy and Pascal Poupart
AAAI Spring Symposium on Computational Physiology, Stanford, CA, 2011.
[paper.pdf]
Ambulatory Measurement of Dual-Tasking Behaviour: Method and Preliminary Evaluation in Older Adults James Y. Tung, Eric A. Roy and Pascal Poupart
International Conference on Ambulatory Monitoring of Physical Activity and Movement (ICAMPAM), Glasgow, UK, 2011.
[paper.pdf]
2010
Bayesian Reinforcement Learning Pascal Poupart
Encyclopedia of Machine Learning, Editors: Claude Sammut and Geoffrey I. Webb, Springer, pages 90-93, 2010.
[link to encyclopedia]
Partially Observable MarkovcDecision Processes Pascal Poupart
Encyclopedia of Machine Learning, Editors: Claude Sammut and Geoffrey I. Webb, Springer, pages 754-760, 2010.
[link to encyclopedia]
Comparative Analysis of Probabilistic Models for Activity Recognition with an Instrumented Walker Farheen Omar, Mathieu Sinn, Jakub Truszkowski, Pascal Poupart, James Tung and Allan Caine
Uncertainty in Artificial Intelligence (UAI), Catalina, CA, 2010.
[paper.pdf]
Automated Handwashing Assistance for Persons with Dementia Using Video and a Partially Observable Markov Decision Process Jesse Hoey, Pascal Poupart, Axel von Bertoldi, Tamy Craig, Craig Boutilier and Alex Mihailidis
Computer Vision and Image Understanding (CVIU), Volume 114, Issue 5, pages 503-519, May 2010.
[paper.pdf][software]
Evaluation Results for a Query-Based Diagnostics Application John Mark Agosta, Omar Zia Khan and Pascal Poupart
European Workshop on Probabilistic Graphical Models (PGM), Helsinki,
Finland, 2010.
[paper.pdf]
Activity Recognition for Users of Rolling Walker Mobility Aids Mathieu Sinn and Pascal Poupart
Workshop on Machine Learning for Assistive Technologies at the International Conference on Neural Information Processing Systems (NIPS), Whistler,
BC, 2010.
[paper.pdf]
Refining Diagnostic POMDPs with User Feedback Omar Zia Khan, Pascal Poupart and John-Mark Agosta
POMDP Practitioners Workshop: Solving Real-World POMDP Problems at the International Conference on Automated Planning and Scheduling (ICAPS), Toronto, ON, 2010.
[paper.pdf]
Automatic Speech Feature Extraction for Cognitive Load Classification Kiril Gorovoy, James Tung and Pascal Poupart
Conference of the Canadian Medical and Biological Engineering Society (CMBEC), Vancouver, BC, 2010.
[paper.pdf]
2009
Minimal Sufficient Explanations for Factored Markov Decision Processes Omar Zia Khan, Pascal Poupart and James Black
International Conference on Automated Planning and Scheduling (ICAPS), Thessaloniki, Greece, 2009.
[paper.pdf]
Towards a Mobility Diagnostic Tool: Tracking Rollator Users� Leg Pose With a Monocular Vision System Samantha Ng, Adel Fakih, Adam Fourney, Pascal Poupart and John Zelek
International Conference of IEEE Engineering in Medicine and Biology Society (EMBC), Minneapolis, 2009.
[paper.pdf]
Probabilistic 3D Tracking: Rollator User's Leg Pose from Coronal Images Samantha Ng, Adel Fakih, Adam Fourney, Pascal Poupart and John Zelek
Canadian Conference on Computer and Robot Vision (CRV), Kelowna, BC, 2009.
[paper.pdf]
2008
Partially Observable Markov Decision Processes with Continuous Observations for Dialog Management Jason Williams, Pascal Poupart and Steve Young
Recent Trends in Discourse and Dialogue, Editors L. Dybkjaer and W. Minker, Springer, pages 191-217, 2008.
[paper.pdf]
Towards Global Reinforcement Learning Milen Pavlov and Pascal Poupart,
NIPS Workshop on Model Uncertainty and Risk in Reinforcement Learning, Vancouver BC, 2008.
[paper.pdf]
Explaining Recommendations Generated by MDPs Omar Zia Khan, Pascal Poupart and Jay Black,
ECAI Workshop on Explanation Aware Computing, Patras, Greece,
2008.
[paper.pdf]
"Is the Sky Pure Today?" AwkChecker an Assistive Tool for Detecting and Correcting Collocation Errors Taehyuen Park, Edward Lank, Pascal Poupart and Michael Terry
ACM Symposium on User Interface Software and Technology (UIST), Monterrey, California, 2008.
[paper.pdf]
Efficient ADD Operations for Point-Based Algorithms Guy Shani, Ronen I. Brafman, Solomon E. Shimony and Pascal Poupart
In Proceedings of the Eighteenth International Conference on Automated Planning and Scheduling (ICAPS), Sydney, Australia, 2008.
[paper.pdf]
Hierarchical POMDP Controller Optimization by Likelihood Maximization Marc Toussaint, Laurent Charlin and Pascal Poupart
In Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence (UAI), Helsinki, Finland, 2008.
[paper.pdf] best paper award runner up
Exploiting Causal Independence Using Weighted Model Counting Wei Li, Pascal Poupart and Peter van Beek
In Proceedings of the 23rd National Conference on Artificial Intelligence (AAAI), Chicago, Illinois, 2008.
[paper.pdf]
Model-based Bayesian Reinforcement Learning in Partially Observable Domains Pascal Poupart and Nikos Vlassis
International Symposium on Artificial Intelligence and Mathematics (ISAIM), Fort Lauderdale, Florida, 2008.
[paper.pdf]
2007
Generating Lexical Analogies using Dependency Relations Andy Chiu, Pascal Poupart and Chrysanne DiMarco
In Proceedings of the International Conference on Empirical Methods in Natural Language Processing (EMNLP), Prague, Czech Republic, 2007.
[paper.pdf]
Assisting Persons with Dementia during Handwashing Using a Partially Observable Markov Decision Process Jesse Hoey, Axel von Bertoldi, Pascal Poupart, and Alex Mihailidis
In Proceedings of the International Conference on Vision Systems (ICVS), Biefeld, Germany, 2007.
[paper.pdf][software] best pape award
2006
Point-Based Value Iteration for Continuous POMDPs Josep M. Porta, Nikos Vlassis, Matthijs T.J. Spaan and Pascal Poupart
Journal of Machine Learning Research, Volume 7, pages 2329-2367, November 2006.
[paper.pdf]
Constraint-based Optimization and Utility Elicitation using the Minimax Decision Criteria Craig Boutilier, Relu Patrascu, Pascal Poupart and Dale Schuurmans
Artificial Intelligence, volume 170, numbers 8-9, pages 686-713, June 2006.
[paper.pdf]
A Planning System Based on Markov Decision Processes to Guide People with Dementia through Activities of Daily Living Jennifer Boger, Jesse Hoey, Pascal Poupart, Craig Boutilier, Geoff Fernie and Alex Mihailidis
IEEE Transactions on Information Technology and Biomedicine, volume 10,
issue 2, pages 323-333, April 2006.
[paper.pdf]
Automated Hierarchy Discovery for Planning in Partially Observable Environments Laurent Charlin, Pascal Poupart and Romy Shioda
In Advances in Neural Information Processing Systems 19 (NIPS), Vancouver, BC, 2006.
[paper.pdf]
Bayesian Reputation Modeling in E-Marketplaces Sensitive to Subjectivity, Deception and Change Kevin Regan, Pascal Poupart and Robin Cohen
In Proceedings of the 21st National Conference on Artificial Intelligence (AAAI), Boston, MA, USA, 2006.
[paper.pdf]
Performing Incremental Bayesian Inference by Dynamic Model Counting Wei Li, Peter van Beek and Pascal Poupart
In Proceedings of the 21st National Conference on Artificial Intelligence (AAAI), Boston, MA, USA, 2006.
[paper.pdf]
Compact, Convex Upper Bound Iteration for Approximate POMDP Planning Tao Wang, Pascal Poupart, Michael Bowling and Dale Schuurmans
In Proceedings of the 21st National Conference on Artificial Intelligence (AAAI), Boston, MA, USA, 2006.
[paper.pdf]
An Analytic Solution to Discrete Bayesian Reinforcement Learning Pascal Poupart, Nikos Vlassis, Jesse Hoey and Kevin Regan
In Proceedings of the 23rd International Conference on Machine Learning (ICML), pages 697-704, Pittsburgh, Pennsylvania, USA, 2006.
[paper.pdf][presentation.pdf]
Learning Lexical Semantic Relations using Lexical Analogies Andy Chiu, Pascal Poupart and Chrysanne DiMarco
Ontologies in Text Technology Workshop, Osnabrueck, Germany, 2006.
[paper.pdf]
2005
The Advisor-POMDP: A Principled Approach to Trust through Reputation in Electronic Markets Kevin Regan, Robin Cohen and Pascal Poupart
In Proceedings of the Third Annual Conference on Privacy, Security and Trust (PST), pages 121-130, St. Andrews, New Brunswick, Canada, 2005.
[paper.pdf]
A Decision-Theoretic Approach to Task Assistance for Persons with Dementia Jennifer Boger, Pascal Poupart, Jesse Hoey, Craig Boutilier, Geoff Fernie, and Alex Mihailidis
In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 1293-1299, Edinburgh, Scotland, 2005.
[paper.pdf][software]
Regret-based Utility Elicitation in Constraint-based Decision Problems Craig Boutilier, Relu Patrscu, Pascal Poupart and Dale Schuurmans
In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 929-934, Edinburgh, Scotland, 2005.
[paper.pdf]
Solving POMDPs with Continuous or Large Discrete Observation Spaces Jesse Hoey and Pascal Poupart
In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 1332-1338, Edinburgh, Scotland, 2005.
[paper.pdf]
POMDP Models for Assistive Technology Jesse Hoey, Pascal Poupart, Craig Boutilier and Alex Mihailidis
In Proceedings of the AAAI Fall Symposium on Caring Machines: AI in Eldercare, Stanford, CA, 2005.
[paper.pdf]
Partially Observable Markov Decision Processes with Continuous Observations for Dialogue Management Jason D. Williams, Pascal Poupart and Steve Young
In Proceedings of the 6th SigDial Workshop on Discourse and Dialogue, Lisbon, Portugal, 2005.
[paper.pdf]
Factored Partially Observable Markov Decision Processes for Dialogue Management Jason D. Williams, Pascal Poupart and Steve Young
In Proceedings of the 4th IJCAI Workshop on Knowledge and Reasoning in Practical Dialog Systems, Edinburgh, Scotland, 2005.
[paper.pdf]
Semi-Supervised Learning of a POMDP Model of Patient-Caregiver Interactions Jesse Hoey, Pascal Poupart, Craig Boutilier and Alex Mihailidis
In Proceedings of the IJCAI Workshop "Modeling Others From Observations" (MOO '05), Edinburgh, Scotland, 2005.
[paper.pdf]
Exploiting Structure to Efficiently Solve Large Scale Partially Observable Markov Decision Processes Pascal Poupart
Ph.D. thesis, Department of Computer Science, University of
Toronto, Toronto, 2005.
[thesis.pdf][software]
Using Factored Partially Observable Markov Decision Processes with Continuous Observations for Dialogue Management Jason D. Williams, Pascal Poupart and Steve Young
Cambridge University Engineering Department Technical Report: CUED/F-INFENG/TR.520, March 2005.
[techreport.pdf]
2004
VDCBPI: an Approximate Scalable Algorithm for Large Scale POMDPs Pascal Poupart and Craig Boutilier
In Advances in Neural Information Processing Systems 17 (NIPS), pages 1081-1088, Vancouver, BC, 2004.
[paper.pdf]
2003
Bounded Finite State Controllers Pascal Poupart and Craig Boutilier
In Advances in Neural Information Processing Systems 16 (NIPS), Vancouver, BC, 2003.
[paper.pdf][NIPS presentation html][NIPS poster html]
Constraint-based Optimization with the Minimax Decision Criterion Craig Boutilier, Relu Patrascu, Pascal Poupart and Dale Schuurmans
In Proceedings of the Ninth International Conference on Principles and Practice of Constraint Programming (CP), pages 168-182, Kinsale, Ireland, 2003.
[paper.pdf]
Using a POMDP Controller to Guide Persons With Dementia Through Activities of Daily Living Jennifer Boger, Goeff Fernie, Pascal Poupart and Alex Mihailidis
In the Adjunct Proceedings of the Fifth International Conference on Ubiquitous Computing (UBICOMP), pages 219-220, Seattle, WA, 2003.
[abstract.pdf]
2002
Value-directed Compression of POMDPs Pascal Poupart and Craig Boutilier
In Advances in Neural Information Processing Systems 15 (NIPS), pages 1547-1554, Vancouver, BC, 2002.
[paper.pdf][NIPS poster html]
Piecewise Linear Value Function Approximation for Factored MDPs Pascal Poupart, Craig Boutilier, Relu Patrascu and Dale Schuurmans
In Proceedings of the Eighteenth National Conference on Artificial Intelligence (AAAI), pages 292-299, Edmonton, AB, 2002.
[paper.pdf][AAAI poster html]
Greedy linear value-approximation for factored Markov decision processes Relu Patrascu, Pascal Poupart, Dale Schuurmans, Craig Boutilier and Carlos Guestrin
In Proceedings of the Eighteenth National Conference on Artificial Intelligence (AAAI), pages 285-291, Edmonton, AB, 2002.
[paper.pdf]
2001
Value-Directed Sampling Methods for Monitoring POMDPs Pascal Poupart, Louis E. Ortiz and Craig Boutilier
In Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence (UAI), pages 453-461, Seattle, WA, 2001.
[paper.pdf][UAI presentation html]
Vector-Space Analysis of Belief-State Approximation for POMDPs Pascal Poupart and Craig Boutilier
In Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence (UAI), pages 445-452, Seattle, WA, 2001.
[paper.pdf][UAI poster html]
2000
Value-Directed Belief State Approximation for POMDPs Pascal Poupart and Craig Boutilier
In Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI), pages 497-506, Stanford, CA, 2000.
[paper.pdf][UAI poster html]
Approximate Value-Directed Belief State Monitoring for Partially Observable Markov Decision Processes Pascal Poupart
Master's thesis, Department of Computer Science, University of
British Columbia, Vancouver, 2000.
[thesis.pdf]