Search Results for author: Sayantan Choudhury

Found 6 papers, 2 papers with code

Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates

no code implementations8 Jun 2023 Siqi Zhang, Sayantan Choudhury, Sebastian U Stich, Nicolas Loizou

However, with the increase of minimax optimization and variational inequality problems in machine learning, the necessity of designing efficient distributed/federated learning approaches for these problems is becoming more apparent.

Federated Learning

Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions

1 code implementation NeurIPS 2023 Sayantan Choudhury, Eduard Gorbunov, Nicolas Loizou

In addition, several important questions regarding the convergence properties of these methods are still open, including mini-batching, efficient step-size selection, and convergence guarantees under different sampling strategies.

Circuit Complexity From Cosmological Islands

no code implementations16 Dec 2020 Sayantan Choudhury, Satyaki Chowdhury, Nitin Gupta, Anurag Mishara, Sachin Panneer Selvam, Sudhakar Panda, Gabriel D. Pasquino, Chiranjeeb Singha, Abinash Swain

By studying the cosmological circuit complexity, Out-of-Time Ordered Correlators, and entanglement entropy of the modes of the squeezed state, in different parameter spaces, we conclude the non-universality of these measures.

High Energy Physics - Theory Disordered Systems and Neural Networks General Relativity and Quantum Cosmology Chaotic Dynamics Quantum Physics

Chaos and Complexity from Quantum Neural Network: A study with Diffusion Metric in Machine Learning

no code implementations16 Nov 2020 Sayantan Choudhury, Ankan Dutta, Debisree Ray

In this work, our prime objective is to study the phenomena of quantum chaos and complexity in the machine learning dynamics of Quantum Neural Network (QNN).

BIG-bench Machine Learning Learning Theory

The Generalized OTOC from Supersymmetric Quantum Mechanics: Study of Random Fluctuations from Eigenstate Representation of Correlation Functions

no code implementations6 Aug 2020 Kaushik Y. Bhagat, Baibhab Bose, Sayantan Choudhury, Satyaki Chowdhury, Rathindra N. Das, Saptarshhi G. Dastider, Nitin Gupta, Archana Maji, Gabriel D. Pasquino, Swaraj Paul

The concept of out-of-time-ordered correlation (OTOC) function is treated as a very strong theoretical probe of quantum randomness, using which one can study both chaotic and non-chaotic phenomena in the context of quantum statistical mechanics.

High Energy Physics - Theory Disordered Systems and Neural Networks General Relativity and Quantum Cosmology Chaotic Dynamics Quantum Physics

Cannot find the paper you are looking for? You can Submit a new open access paper.