147 citations · 194 across the 25 of their papers we have counts for
28 papers
Optimal Compression of Unit Norm Vectors in the High Distortion Regime
Heng Zhu, Avishek Ghosh, Arya Mazumdar
Motivated by the need for communication-efficient distributed learning, we investigate the method for compressing a unit norm vector into the minimum number of bits, while still al…
Model Selection in Reinforcement Learning with General Function Approximations
Avishek Ghosh, Sayak Ray Chowdhury
We consider model selection for classic Reinforcement Learning (RL) environments -- Multi Armed Bandits (MABs) and Markov Decision Processes (MDPs) -- under general function approx…
Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference
Debangshu Banerjee, Avishek Ghosh, Sayak Ray Chowdhury +1
We present a non-asymptotic lower bound on the eigenspectrum of the design matrix generated by any linear bandit algorithm with sub-linear regret when the action set has well-behav…
Decentralized Competing Bandits in Non-Stationary Matching Markets
Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran +2
Understanding complex dynamics of two-sided online matching markets, where the demand-side agents compete to match with the supply-side (arms), has recently received substantial in…
On Learning Mixture of Linear Regressions in the Non-Realizable Setting
Avishek Ghosh, Arya Mazumdar, Soumyabrata Pal +1
While mixture of linear regressions (MLR) is a well-studied topic, prior works usually do not analyze such models for prediction error. In fact, {\em prediction} and {\em loss} are…
Breaking the Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits
Avishek Ghosh, Abishek Sankararaman
We prove an instance independent (poly) logarithmic regret for stochastic contextual bandits with linear payoff. Previously, in \cite{chu2011contextual}, a lower bound of $\mathcal…
Model Selection for Generic Reinforcement Learning
Avishek Ghosh, Sayak Ray Chowdhury, Kannan Ramchandran
We address the problem of model selection for the finite horizon episodic Reinforcement Learning (RL) problem where the transition kernel belongs to a family of models $\math…
Model Selection for Generic Contextual Bandits
Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran
We consider the problem of model selection for the general stochastic contextual bandits under the realizability assumption. We propose a successive refinement based algorithm call…
LocalNewton: Reducing Communication Bottleneck for Distributed Learning
Vipul Gupta, Avishek Ghosh, Michal Derezinski +3
To address the communication bottleneck problem in distributed optimization within a master-worker framework, we propose LocalNewton, a distributed second-order algorithm with loca…
Escaping Saddle Points in Distributed Newton's Method with Communication Efficiency and Byzantine Resilience
Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar +1
The problem of saddle-point avoidance for non-convex optimization is quite challenging in large scale distributed learning frameworks, such as Federated Learning, especially in the…
Distributed Newton Can Communicate Less and Resist Byzantine Workers
Avishek Ghosh, Raj Kumar Maity, Arya Mazumdar
We develop a distributed second order optimization algorithm that is communication-efficient as well as robust against Byzantine failures of the worker machines. We propose COMRADE…
Problem-Complexity Adaptive Model Selection for Stochastic Linear Bandits
Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran
We consider the problem of model selection for two popular stochastic linear bandit settings, and propose algorithms that adapts to the unknown problem complexity. In the first set…
An Efficient Framework for Clustered Federated Learning
Avishek Ghosh, Jichan Chung, Dong Yin +1
We address the problem of federated learning (FL) where users are distributed and partitioned into clusters. This setup captures settings where different groups of users have their…
Alternating Minimization Converges Super-Linearly for Mixed Linear Regression
Avishek Ghosh, Kannan Ramchandran
We address the problem of solving mixed random linear equations. We have unlabeled observations coming from multiple linear regressions, and each observation corresponds to exactly…
Communication-Efficient and Byzantine-Robust Distributed Learning with Error Feedback
Avishek Ghosh, Raj Kumar Maity, Swanand Kadhe +2
We develop a communication-efficient distributed learning algorithm that is robust against Byzantine worker machines. We propose and analyze a distributed gradient-descent algorith…
Max-Affine Regression: Provable, Tractable, and Near-Optimal Statistical Estimation
Avishek Ghosh, Ashwin Pananjady, Adityanand Guntuboyina +1
Max-affine regression refers to a model where the unknown regression function is modeled as a maximum of unknown affine functions for a fixed . This generalizes linea…
Robust Federated Learning in a Heterogeneous Environment
Avishek Ghosh, Justin Hong, Dong Yin +1
We study a recently proposed large-scale distributed learning paradigm, namely Federated Learning, where the worker machines are end users' own devices. Statistical and computation…
Online Scoring with Delayed Information: A Convex Optimization Viewpoint
Avishek Ghosh, Kannan Ramchandran
We consider a system where agents enter in an online fashion and are evaluated based on their attributes or context vectors. There can be practical situations where this context is…
Faster Data-access in Large-scale Systems: Network-scale Latency Analysis under General Service-time Distributions
Avishek Ghosh, Kannan Ramchandran
In cloud storage systems with a large number of servers, files are typically not stored in single servers. Instead, they are split, replicated (to ensure reliability in case of ser…
Matching Observations to Distributions: Efficient Estimation via Sparsified Hungarian Algorithm
Sinho Chewi, Forest Yang, Avishek Ghosh +2
Suppose we are given observations, where each observation is drawn independently from one of known distributions. The goal is to match each observation to the distribution from…
Asynchronous Stochastic Approximation Based Learning Algorithms for As-You-Go Deployment of Wireless Relay Networks along a Line
Arpan Chattopadhyay, Avishek Ghosh, Anurag Kumar
We are motivated by the need for impromptu (or as-you-go) deployment of multihop wireless networks, by human agents or robots; the agent moves along a line, makes wireless link qua…
Misspecified Linear Bandits
Avishek Ghosh, Sayak Ray Chowdhury, Aditya Gopalan
We consider the problem of online learning in misspecified linear stochastic multi-armed bandit problems. Regret guarantees for state-of-the-art linear bandit algorithms such as Op…
Impromptu Deployment of Wireless Relay Networks: Experiences Along a Forest Trail
Arpan Chattopadhyay, Avishek Ghosh, Akhila S. Rao +4
We are motivated by the problem of impromptu or as- you-go deployment of wireless sensor networks. As an application example, a person, starting from a sink node, walks along a for…
Multi-robot Cooperative Box-pushing problem using Multi-objective Particle Swarm Optimization Technique
Arnab Ghosh, Avishek Ghosh, Arkabandhu Chowdhury +2
The present work provides a new approach to solve the well-known multi-robot co-operative box pushing problem as a multi objective optimization problem using modified Multi-objecti…