Skip to content

Author

Adam Ousherovitch

We have 3 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Entropy Regularization: A Free Correction to Cross-Entropy for Verified Demonstrations

It is shown that minimizing cross-entropy can be misaligned with minimizing verifier risk; two policies can assign identical likelihood to the observed demonstrations while placing different probability mass on incorrect outputs, and entropy-regularized training consistently improves verifier accuracy over standard cro...

Mihir Dhanakshirur, Adam Ousherovitch, A. Tewari · 0 citations
#artificial intelligence Preprint Sep 2026

Terminal Shrinkage Averaging Reveals a Schedule-Estimator Interaction in LLM Pretraining

This work proposes TSA, which interpolates between the raw final iterate and the average of recent checkpoints to balance recent progress against terminal variation and demonstrates that the resulting gains transfer to depth-22 NanoChat, where the combined schedule and estimator improve validation quality.

Adam Ousherovitch, Yi-Xin Wang · 0 citations
#artificial intelligence Preprint Sep 2026

Direct Optimization of Generators for Search in Automated Theorem Proving

This work extends Compute-Aligned Training to this setting through an abstraction of policy-guided search, deriving tractable, trace-supported losses and introduces a search-agnostic uniform-allocation (UA) loss that accounts for the budget without specifying the specific search.

Adam Ousherovitch, A. Tewari · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.