4 papers
High-Probability PL-SGD with Markovian Noise: Optimal Mixing and Tail Dependence
Dhruv Sarkar, Aprameyo Chakrabartty, Vaneet Aggarwal
We study first-order methods for smooth objectives satisfying the Polyak-Åojasiewicz (PL) condition when gradient samples are generated by an exogenous Markov chain. In the light-…
Projection-free Algorithms for Online Convex Optimization with Adversarial Constraints
Dhruv Sarkar, Aprameyo Chakrabartty, Subhamon Supantha +2
We study a generalization of the Online Convex Optimization (OCO) framework with time-varying adversarial constraints. In this setting, at each round, the learner selects an action…
TAPS : Frustratingly Simple Test Time Active Learning for VLMs
Dhruv Sarkar, Aprameyo Chakrabartty, Bibhudatta Bhanja
Test-Time Optimization enables models to adapt to new data during inference by updating parameters on-the-fly. Recent advances in Vision-Language Models (VLMs) have explored learni…
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…