collaborators

6 papers

cs.LG2026

Scaling Limits of Constant-Stepsize SGD at Flat Minima

Jingyi Zhang, Cheng Mao, Debankur Mukherjee

For stochastic gradient descent (SGD) with a constant stepsize , the invariant law of the iterates, centered at a minimizer, describes the behavior of the algorithm over long t…

math.PR2026

Waning Immunity Fails to Restore a Positive Epidemic Threshold on Power-Law Networks

Zihao He, Souvik Dhara, Debankur Mukherjee

In a seminal work, Chatterjee and Durrett (2009) established that for the SIS epidemic process on random graphs with power-law degree distributions, the infection survives for an e…

math.PR2026

Higher-Order Approximations of Sojourn Times in M/G/1 Queues via Stein's Method

Bihan Chatterjee, Siva Theja Maguluri, Debankur Mukherjee

We study the stationary sojourn time distribution in an M/G/1 queue operating under heavy traffic. It is known that the sojourn time converges to an exponential distribution in the…

cs.LG2026

SCaLE: Switching Cost aware Learning and Exploration

Neelkamal Bhuyan, Debankur Mukherjee, Adam Wierman

This work addresses the fundamental problem of unbounded metric movement costs in bandit online convex optimization, by considering high-dimensional dynamic quadratic hitting costs…

math.PR2025

Many-server asymptotics for Join-the-Shortest Queue in the Super-Halfin-Whitt Scaling Window

Zhisheng Zhao, Sayan Banerjee, Debankur Mukherjee

The Join-the-Shortest Queue (JSQ) policy is a classical benchmark for the performance of many-server queueing systems due to its strong optimality properties. While the exact analy…

math.OC2025

Optimal Decentralized Smoothed Online Convex Optimization

Neelkamal Bhuyan, Debankur Mukherjee, Adam Wierman

We study the multi-agent Smoothed Online Convex Optimization (SOCO) problem, where agents interact through a communication graph. In each round, each agent receives a stron…