3 papers
cs.LG2026
Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
Ved Sriraman, Peihan Liu, Daniel Hsu +1
Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model tra…
cs.LG2026
Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment
Ved Sriraman, Adam Block
Best-of-N (BoN) sampling is a widely used inference-time alignment method for language models, whereby N candidate responses are sampled from a reference model and the one with the…
cs.LG2025
Active Learning via Regression Beyond Realizability
Atul Ganju, Shashaank Aiyer, Ved Sriraman +1
We present a new active learning framework for multiclass classification based on surrogate risk minimization that operates beyond the standard realizability assumption. Existing s…