6 citations · 10 across the 7 of their papers we have counts for
7 papers
Beyond Parameter Count: Implicit Bias in Soft Mixture of Experts
Youngseog Chung, Dhruv Malik, Jeff Schneider +2
The traditional viewpoint on Sparse Mixture of Experts (MoE) models is that instead of training a single large expert, which is computationally expensive, we can train many small e…
Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
Aakash Lahoti, Stefani Karp, Ezra Winston +2
Vision tasks are characterized by the properties of locality and translation invariance. The superior performance of convolutional neural networks (CNNs) on these tasks is widely a…
Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality
Dhruv Malik, Conor Igoe, Yuanzhi Li +1
In recommender system or crowdsourcing applications of online learning, a human's preferences or abilities are often a function of the algorithm's recent actions. Motivated by this…
How Does Adaptive Optimization Impact Local Neural Network Geometry?
Kaiqi Jiang, Dhruv Malik, Yuanzhi Li
Adaptive optimization methods are well known to achieve superior convergence relative to vanilla gradient methods. The traditional viewpoint in optimization, particularly in convex…
Complete Policy Regret Bounds for Tallying Bandits
Dhruv Malik, Yuanzhi Li, Aarti Singh
Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that e…
Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Dhruv Malik, Aldo Pacchiano, Vishwak Srinivasan +1
Reinforcement learning (RL) is empirically successful in complex nonlinear Markov decision processes (MDPs) with continuous state spaces. By contrast, the majority of theoretical R…
When Is Generalizable Reinforcement Learning Tractable?
Dhruv Malik, Yuanzhi Li, Pradeep Ravikumar
Agents trained by reinforcement learning (RL) often fail to generalize beyond the environment they were trained in, even when presented with new scenarios that seem similar to the…