activity
20122022
most citedAn Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias

14 citations · 57 across the 13 of their papers we have counts for

collaborators

19 papers

math.OC2022

Stochastic Zeroth-order Functional Constrained Optimization: Oracle Complexity and Applications

Anthony Nguyen, Krishnakumar Balasubramanian

Functionally constrained stochastic optimization problems, where neither the objective function nor the constraint functions are analytically available, arise frequently in machine…

stat.ML20221 cited

Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance

Nuri Mert Vural, Lu Yu, Krishnakumar Balasubramanian +2

We study stochastic convex optimization under infinite noise variance. Specifically, when the stochastic gradient is unbiased and has uniformly bounded -th moment, for some…

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…

math.ST20214 cited

On Empirical Risk Minimization with Dependent and Heavy-Tailed Data

Abhishek Roy, Krishnakumar Balasubramanian, Murat A. Erdogdu

In this work, we establish risk bounds for the Empirical Risk Minimization (ERM) with both dependent and heavy-tailed data-generating processes. We do so by extending the seminal w…

stat.ML20215 cited

Nonparametric Modeling of Higher-Order Interactions via Hypergraphons

Krishnakumar Balasubramanian

We study statistical and algorithmic aspects of using hypergraphons, that are limits of large hypergraphs, for modeling higher-order interactions. Although hypergraphons are extrem…