3.4k citations
- Google (United States)US82 papers
- Google (United Kingdom)GB61 papers
- Massachusetts Institute of TechnologyUS14 papers
- University of OxfordGB12 papers
- École Normale Supérieure - PSLFR10 papers
- Institut national de recherche en sciences et technologies du numériqueFR10 papers
- University College LondonGB10 papers
- University of TorontoCA10 papers
- Imperial College LondonGB9 papers
- McGill UniversityCA9 papers
- University of CambridgeGB8 papers
- Centre de Recherche en InformatiqueFR7 papers
19 papers · 2 filters
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity
Ran Liu, Mehdi Azabou, Max Dabagia +5
Meaningful and simplified representations of neural activity can yield insights into how and what information is being processed within a neural circuit. However, without labels, f…
ETA Prediction with Graph Neural Networks in Google Maps
Austin Derrow-Pinion, Jennifer She, David Wong +14
Travel-time prediction constitutes a task of high importance in transportation networks, with web mapping services like Google Maps regularly serving vast quantities of travel time…
On the Role of Optimization in Double Descent: A Least Squares Study
Ilja Kuzborskij, Csaba Szepesvári, Omar Rivasplata +2
Empirically it has been observed that the performance of deep neural networks steadily improves as we increase model size, contradicting the classical view on overfitting and gener…
Imitation by Predicting Observations
Andrew Jaegle, Yury Sulsky, Arun Ahuja +3
Imitation learning enables agents to reuse and adapt the hard-won expertise of others, offering a solution to several key challenges in learning behavior. Although it is easy to ob…
Robust Learning-Augmented Caching: An Experimental Study
Jakub Chłędowski, Adam Polak, Bartosz Szabucki +1
Effective caching is crucial for the performance of modern-day computing systems. A key optimization problem arising in caching -- which item to evict to make room for a new item -…
Emphatic Algorithms for Deep Reinforcement Learning
Ray Jiang, Tom Zahavy, Zhongwen Xu +4
Off-policy learning allows us to learn about possible policies of behavior from experience generated by a different behavior policy. Temporal difference (TD) learning algorithms ca…