Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
One-Shot Private Confidence Regions via Resampling
Shourya Pandey, Purnamrita Sarkar, Po-Ling Loh +1
We propose a simple framework for constructing differentially private confidence regions \textit{in one shot}, i.e., by adding noise only to the final resampling quantile instead o…
stat.ML2026
Optimal Self-Distillation for Rectified Flow via Linear Probing
Saptarshi Roy, Debepsita Mukherjee, Pratik Patil
Modern generative models are increasingly trained using model-generated signals, creating both opportunities for self-improvement and risks of collapse. We study optimal self-disti…