activity
20122025
most citedAn Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias

14 citations · 59 across the 20 of their papers we have counts for

collaborators
Showing math.STShow all

10 papers · 1 filter

math.ST2024

A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers

Ye He, Alireza Mousavi-Hosseini, Krishnakumar Balasubramanian +1

We study the complexity of heavy-tailed sampling and present a separation result in terms of obtaining high-accuracy versus low-accuracy guarantees i.e., samplers that require only…

math.ST2023

Online covariance estimation for stochastic gradient descent under Markovian sampling

Abhishek Roy, Krishnakumar Balasubramanian

We investigate the online overlapping batch-means covariance estimator for Stochastic Gradient Descent (SGD) under Markovian sampling. Convergence rates of order $O\big(\sqrt{d}\,n…

math.ST2023

Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent

Tianle Liu, Promit Ghosal, Krishnakumar Balasubramanian +1

Stein Variational Gradient Descent (SVGD) is a nonparametric particle-based deterministic sampling algorithm. Despite its wide usage, understanding the theoretical properties of SV…

math.ST20231 cited

Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein Space

Michael Diao, Krishnakumar Balasubramanian, Sinho Chewi +1

Variational inference (VI) seeks to approximate a target distribution by an element of a tractable family of distributions. Of key interest in statistics and machine learning i…

math.ST20224 cited

Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlo

Krishnakumar Balasubramanian, Sinho Chewi, Murat A. Erdogdu +2

For the task of sampling from a density on , where is possibly non-convex but -gradient Lipschitz, we prove that averaged Langevin Monte Ca…

math.ST2022

Heavy-tailed Sampling via Transformed Unadjusted Langevin Algorithm

Ye He, Krishnakumar Balasubramanian, Murat A. Erdogdu

We analyze the oracle complexity of sampling from polynomially decaying heavy-tailed target densities based on running the Unadjusted Langevin Algorithm on certain transformed vers…