activity
20232026
most citedPartial projected ensembles and spatiotemporal structure of information scrambling

2 citations · 3 across the 6 of their papers we have counts for

collaborators

6 papers

cs.NI2026

GATE: GPU-Accelerated Traffic Engineering for the WAN

Rahul Bothra, Alexander Krentsel, Saptarshi Mandal +4

Traffic engineering (TE) has become a crucial tool for enforcing routing policy and maintaining operational efficiency in large networks. Existing TE solutions pick an objective fu…

cs.LG2025

Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function Approximation

Saptarshi Mandal, Yashaswini Murthy, R. Srikant

Distributionally robust reinforcement learning seeks policies that remain effective when the deployment environment differs from the one that generated the training data. We study…

quant-ph2025★ 2 cited

Partial projected ensembles and spatiotemporal structure of information scrambling

Saptarshi Mandal, Pieter W. Claeys, Sthitadhi Roy

Thermalisation and information scrambling in out-of-equilibrium quantum many-body systems are deeply intertwined: local subsystems dynamically approach thermal density matrices whi…

physics.flu-dyn2025

Thermal transport characteristics of impinging ferrofluid droplets in the presence of a magnetic field

Ram Krishna Shah, Saptarshi Mandal

Droplet interactions with solid surfaces are fundamental to natural phenomena and hold significant commercial relevance across diverse applications. While the impingement dynamics…

cs.LG2024★ 1 cited

A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networks

Saptarshi Mandal, Xiaojun Lin, R. Srikant

Knowledge distillation, where a small student model learns from a pre-trained large teacher model, has achieved substantial empirical success since the seminal work of \citep{hinto…

cs.LG2023

Spectral Clustering for Crowdsourcing with Inherently Distinct Task Types

Saptarshi Mandal, Seo Taek Kong, Dimitrios Katselis +1

The Dawid-Skene model is the most widely assumed model in the analysis of crowdsourcing algorithms that estimate ground-truth labels from noisy worker responses. In this work, we a…