research
∙
05/02/2023
The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
We develop information-geometric techniques to analyze the trajectories ...
share
research
∙
10/31/2022
A picture of the space of typical learnable tasks
We develop a technique to analyze representations learned by deep networ...
research
∙
08/23/2022
The Value of Out-of-Distribution Data
More data helps us generalize to a task. But real datasets can contain o...
research
∙
02/01/2022
Deep Reference Priors: What is the best way to pretrain a model?
What is the best way to exploit extra data – be it unlabeled data from t...
research
∙
06/06/2021
Boosting a Model Zoo for Multi-Task and Continual Learning
Leveraging data from multiple tasks, either all at once, or incrementall...
research
∙
09/09/2019
Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning
Option discovery and skill acquisition frameworks are integral to the fu...
research
∙
05/14/2019
Successor Options: An Option Discovery Framework for Reinforcement Learning
The options framework in reinforcement learning models the notion of a s...
research
∙
06/12/2018
A Question-Answering framework for plots using Deep learning
Deep Learning has managed to push boundaries in a wide variety of tasks....
research
∙
11/27/2017
AUPCR Maximizing Matchings : Towards a Pragmatic Notion of Optimality for One-Sided Preference Matchings
We consider the problem of computing a matching in a bipartite graph in ...
research
∙
05/20/2017