Donya Saless — accepted AI-conference papers

2026

Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking

Dhruv Rohatgi, Abhishek Shetty, Donya Saless, Yuchen Li, Ankur Moitra, Andrej Risteski +1

ICLR 2026poster

Test-time algorithms that combine the *generative* power of language models with *process verifiers* that assess the quality of partial generations offer a promising lever for eliciting new reasoning capabilities, but the algorithmic design space and computational scaling properties of such approach…

Cited by 0 Source ↗Scholar ↗

2025

PAC Learning with Improvements

Idan Attias, Avrim Blum, Keziah Naggita, Donya Saless, Dravyansh Sharma, Matthew Walter

ICML 2025poster

One of the most basic lower bounds in machine learning is that in nearly any nontrivial setting, it takes at least $1/\epsilon$ samples to learn to error $\epsilon$ (and more, if the classifier being learned is complex). However, suppose that data points are agents who have the ability to improve b…

Cited by 0 Source ↗PDF ↗Scholar ↗