most citedTowards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent

1 citations · 1 across the 3 of their papers we have counts for

collaborators

7 papers

cs.LG2026

Convergence of Steepest Descent and Adam under Non-Uniform Smoothness

Sharan Vaswani, Yifan Sun, Reza Babanezhad

Recent work has analyzed the convergence of first-order methods under non-uniform smoothness assumptions that better model the loss landscape in machine learning tasks. We generali…

cs.LG2026

Dissecting Discrete Soft Actor-Critic: Limitations and Principled Alternatives

Reza Asad, Reza Babanezhad, Sharan Vaswani

While Soft Actor-Critic (SAC) is highly effective in continuous control, its discrete counterpart (DSAC) performs poorly on challenging discrete-action domains such as Atari. Conse…

math.OC20261 cited

Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent

Sharan Vaswani, Benjamin Dubois-Taine, Reza Babanezhad

We aim to make stochastic gradient descent (SGD) adaptive to (i) the noise in the stochastic gradients and (ii) problem-dependent constants. When minimizing smooth, strongly…

cs.LG2026

Towards Parameter-Free Temporal Difference Learning

Yunxiang Li, Mark Schmidt, Reza Babanezhad +1

Temporal difference (TD) learning is a fundamental algorithm for estimating value functions in reinforcement learning. Recent finite-time analyses of TD with linear function approx…

cs.LG2026

Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster

Sharan Vaswani, Reza Babanezhad

Armijo line-search (Armijo-LS) is a standard method to set the step-size for gradient descent (GD). For smooth functions, Armijo-LS alleviates the need to know the global smoothnes…

cs.LG2025

Fast Convergence of Softmax Policy Mirror Ascent

Reza Asad, Reza Babanezhad, Issam Laradji +2

Natural policy gradient (NPG) is a common policy optimization algorithm and can be viewed as mirror ascent in the space of probabilities. Recently, Vaswani et al. [2021] introduced…