regret analysis 2accelerated methods 1algorithm design 1bias correction 1constrained learning 1convergence rates 1exploration strategies 1fairness 1multi-armed bandits 1non-expansive operators 1online convex optimization 1projection methods 1
From the 3 of 15 linked papers with an AI index.
Showing stat.MLShow all
3 papers · 1 filter
stat.ML2026
Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration
Dhruv Sarkar, Vaneet Aggarwal
The paper analyzes two‑time‑scale stochastic approximation with a non‑expansive slow map, establishes sharp lower bounds on residual decay, and proposes bias‑corrected and single‑l…
stat.ML2026
Price of Fairness in Bandits: A Tight Minimax Characterization
Dhruv Sarkar, Soumyadeep Dutta, Sayak Ray Chowdhury
The paper characterizes the exact regret cost of enforcing strict fairness in multi-armed bandits, proving a matching lower bound and presenting the UCB-HARE algorithm that achieve…
stat.ML2025
Relation-Aware Slicing in Cross-Domain Alignment
Dhruv Sarkar, Aprameyo Chakrabartty, Anish Chakrabarty +1
The Sliced Gromov-Wasserstein (SGW) distance, aiming to relieve the computational cost of solving a non-convex quadratic program that is the Gromov-Wasserstein distance, utilizes p…