K
Kanika Madan
Researcher at Université de Montréal
Publications - 5
Citations - 20
Kanika Madan is an academic researcher from Université de Montréal. The author has contributed to research in topics: Reinforcement learning & Initialization. The author has an hindex of 2, co-authored 5 publications receiving 20 citations.
Papers
More filters
Accounting for Variance in Machine Learning Benchmarks
Xavier Bouthillier,Pierre Delaunay,Mirko Bronzi,Assya Trofimov,Brennan Nichyporuk,Justin Szeto,Naz Sepah,Edward Raff,Kanika Madan,Vikram Voleti,Samira Ebrahimi Kahou,Samira Ebrahimi Kahou,Vincent Michalski,Dmitriy Serdyuk,Tal Arbel,Chris Pal,Gaël Varoquaux,Pascal Vincent,Pascal Vincent +18 more
TL;DR: In this paper, the authors show that adding more sources of variation to an imperfect estimator approaches better the ideal estimator at a 51× reduction in compute cost, leading to recommendations for performance comparisons.
Posted Content
Fast and Slow Learning of Recurrent Independent Mechanisms
TL;DR: In this paper, an attention mechanism dynamically selects which modules can be adapted to the current task, and the parameters of the selected modules are allowed to change quickly as the learner is confronted with variations in what it experiences.
Proceedings Article
Meta Attention Networks: Meta-Learning Attention to Modulate Information Between Recurrent Independent Mechanisms
TL;DR: In this article, the authors propose a particular training framework in which the pieces of knowledge an agent needs, as well as its reward function are stationary and can be re-used across tasks, and find that meta-learning the modular aspects of the proposed system greatly help in achieving faster learning, in experiments with a reinforcement learning setup involving navigation in a partially observed grid world with image-level input.
Posted Content
Accounting for Variance in Machine Learning Benchmarks.
Xavier Bouthillier,Pierre Delaunay,Mirko Bronzi,Assya Trofimov,Brennan Nichyporuk,Justin Szeto,Naz Sepah,Edward Raff,Kanika Madan,Vikram Voleti,Samira Ebrahimi Kahou,Samira Ebrahimi Kahou,Vincent Michalski,Dmitriy Serdyuk,Tal Arbel,Chris Pal,Gaël Varoquaux,Pascal Vincent,Pascal Vincent +18 more
TL;DR: In this paper, the authors show that adding more sources of variation to an imperfect estimator approaches better the ideal estimator at a 51 times reduction in compute cost, leading to recommendations for performance comparisons.
Proceedings Article
Fast And Slow Learning Of Recurrent Independent Mechanisms
TL;DR: In this article, an attention mechanism dynamically selects which modules can be adapted to the current task, and the parameters of the selected modules are allowed to change quickly as the learner is confronted with variations in what it experiences.