University of Waterloo COVID-19 update

Please see the University of Waterloo’s frequently asked questions for information about COVID-19 and how it has affected university operations.

Please visit the list of modified services if you have questions about university services.

Although the University of Waterloo is closed for in-person events until further notice, many virtual events and presentations of interest to computer scientists are taking place each week at the Cheriton School of Computer Science. Please check out what our students and faculty are doing.

Priyank Jaini wins second place in the Mathematics Doctoral Prize competition

Friday, April 24, 2020

Recent PhD graduate Priyank Jaini has been awarded second place in the Faculty of Mathematics Doctoral Prize competition. Now in its second year, these prizes are awarded annually to recognize the achievements of top graduating doctoral students in the Faculty of Mathematics. As a silver recipient, Priyank will receive $1,000.

photo of Priyank JainiCo-supervised by Professors Pascal Poupart and Yaoliang Yu, both faculty members at the Cheriton School of Computer Science, Priyank defended his thesis titled Likelihood-based Density Estimation using Deep Architectures in December 2019.

Multivariate density estimation is a central problem in unsupervised machine learning. Several methods have been proposed for density estimation, including classical techniques such histograms, kernel density estimation methods, mixture models, and more recently neural density estimation that leverages recent advances in deep learning and neural networks to tractably represent a density function. Particularly so today, when large amounts of data are being generated in almost every field, it is of paramount importance to develop density estimation methods that are inexpensive, both computationally and in memory cost. The main contribution of Priyank’s thesis was in providing a principled study of parametric density estimation methods using mixture models and triangular maps for neural density estimation.

“Dr. Jaini’s thesis is remarkable in the sense that it makes impactful contributions in terms of both theory and practice,” said Professor Poupart. “His work on sum-of-square polynomial flows represents a foundational contribution that unifies and advances the development of probabilistic neural networks.”

Professor Yu, adds: “Furthermore his work on personalized transfer learning found applications in activity recognition for stroke rehabilitation, sleep stage recognition based on polysomnography data, and network traffic prediction in telecommunication networks.”

While a doctoral student, Priyank was one of 10 recipients nationally to receive a Borealis AI 2019 Graduate Fellowship, a prestigious award conferred to exceptional students pursuing graduate studies in machine learning and artificial intelligence at universities across Canada. He was also a recipient of a David R. Cheriton Graduate Scholarship and Huawei Graduate Fellowship in Artificial Intelligence.

Priyank is currently a postdoctoral researcher working on combining probabilistic generative models and deep learning under the direction of Professor Max Welling at UvA Bosch-Delta Lab in the Netherlands.

  1. 2020 (31)
    1. May (6)
    2. April (13)
    3. March (3)
    4. February (3)
    5. January (6)
  2. 2019 (90)
    1. December (3)
    2. November (8)
    3. October (6)
    4. September (9)
    5. August (7)
    6. July (8)
    7. June (10)
    8. May (5)
    9. April (11)
    10. March (6)
    11. February (10)
    12. January (7)
  3. 2018 (82)
    1. December (6)
    2. November (8)
    3. October (8)
    4. September (12)
    5. August (4)
    6. July (8)
    7. June (8)
    8. May (5)
    9. April (10)
    10. March (6)
    11. February (2)
    12. January (5)
  4. 2017 (50)
  5. 2016 (27)
  6. 2015 (41)
  7. 2014 (32)
  8. 2013 (46)
  9. 2012 (17)
  10. 2011 (20)