5 citations · 6 across the 2 of their papers we have counts for
11 papers
Towards Painless Policy Optimization for Constrained MDPs
Arushi Jain, Sharan Vaswani, Reza Babanezhad +2
We study policy optimization in an infinite horizon, -discounted constrained Markov decision process (CMDP). Our objective is to return a policy that achieves large expected rew…
SVRG Meets AdaGrad: Painless Variance Reduction
Benjamin Dubois-Taine, Sharan Vaswani, Reza Babanezhad +2
Variance reduction (VR) methods for finite-sum minimization typically require the knowledge of problem-dependent constants that are often unknown and difficult to estimate. To addr…
Adaptive Gradient Methods Converge Faster with Over-Parameterization (but you should do a line-search)
Sharan Vaswani, Issam Laradji, Frederik Kunstner +3
Adaptive gradient methods are typically used for training over-parameterized models. To better understand their behaviour, we study a simplistic setting -- smooth, convex losses wi…
Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence
Nicolas Loizou, Sharan Vaswani, Issam Laradji +1
We propose a stochastic variant of the classical Polyak step-size (Polyak, 1987) commonly used in the subgradient method. Although computing the Polyak step-size requires knowledge…
Old Dog Learns New Tricks: Randomized UCB for Bandit Problems
Sharan Vaswani, Abbas Mehrabian, Audrey Durand +1
We propose , a bandit strategy that builds on theoretically derived confidence intervals similar to upper confidence bound (UCB) algorithms, but akin to Thompson sampl…
Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation
Si Yi Meng, Sharan Vaswani, Issam Laradji +2
We consider stochastic second-order methods for minimizing smooth and strongly-convex functions under an interpolation condition satisfied by over-parameterized models. Under this…