Data-driven Policies for Two-stage Stochastic Linear Programs.
Chhavi Sharma, Harsha Gangammanavar
Distributed Accelerated Gradient Methods with Restart under Quadratic Growth Condition
Switch and Conquer: Efficient Algorithms By Switching Stochastic Gradient Oracles For Decentralized Saddle Point Problems
Chhavi Sharma, Vishnu Narayanan, P. Balamurugan
IEEE Conference on Decision and Control, 2023. pdf, Code, Full paper.
Stochastic Gradient Methods with Compressed Communication for Decentralized Saddle Point Problems.
Chhavi Sharma, Vishnu Narayanan, P. Balamurugan
NeurIPS Workshop on Federated Learning: Recent Advances and New Challenges 2022. pdf
A simple and Fast Distributed Accelerated Gradient Method
Chhavi Sharma, Vishnu Narayanan, P. Balamurugan
Optimization for Machine Learning (OPT-ML) NeurIPS workshop, 2019. pdf
Distributed Accelerated Inexact Proximal Gradient Method via System of Coupled Ordinary Differential Equations
Chhavi Sharma, Vishnu Narayanan, P. Balamurugan
NeurIPS workshop on Beyond First Order Methods for ML, 2019. pdf