6 papers
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…
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…
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…
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…
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…
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…