8 papers
Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry
Susmit Sarkar, Abhinav Raghuvanshi, Kushal Chakrabarti +1
We study distributed optimization with stochastic gradients and finite-bit communication modeled by random (unbiased) quantization. We propose q-PDGD, a quantized stochastic primal…
On a Gradient Approach to Chebyshev Center Problems with Applications to Function Learning
Abhinav Raghuvanshi, Mayank Baranwal, Debasish Chatterjee
We introduce , the first gradient-based optimization framework for solving Chebyshev center problems, a fundamental challenge in optimal function learning and geom…
DeepMech: A Machine Learning Framework for Chemical Reaction Mechanism Prediction
Manajit Das, Ajnabiul Hoque, Mayank Baranwal +1
Prediction of complete step-by-step chemical reaction mechanisms (CRMs) remains a major challenge. Whereas the traditional approaches in CRM tasks rely on expert-driven experiments…
On Linear Convergence of Distributed Stochastic Bilevel Optimization over Undirected Networks via Gradient Aggregation
Ajay Tak, Mayank Baranwal
Many large-scale constrained optimization problems can be formulated as bilevel distributed optimization tasks over undirected networks, where agents collaborate to minimize a glob…
Redistributing Rewards Across Time and Agents for Multi-Agent Reinforcement Learning
Aditya Kapoor, Kale-ab Tessera, Mayank Baranwal +4
Credit assignmen, disentangling each agent's contribution to a shared reward, is a critical challenge in cooperative multi-agent reinforcement learning (MARL). To be effective, cre…
Efficiency Boost in Decentralized Optimization: Reimagining Neighborhood Aggregation with Minimal Overhead
Durgesh Kalwar, Mayank Baranwal, Harshad Khadilkar
In today's data-sensitive landscape, distributed learning emerges as a vital tool, not only fortifying privacy measures but also streamlining computational operations. This becomes…