collaborators

6 papers

cs.LG2026

The Fourth Quadrant: A Stylized View of Benign Misfitting

Gireeja Ranade, Anant Sahai

Training error is what we can observe on a training set; test error is the quantity we actually care about. We study linear regression with squared-error in a deterministic

cs.LG2026

Decomposing Prediction Mechanisms for In-Context Recall

Sultan Daniels, Dylan Davis, Dhruv Gautam +3

We introduce a new family of toy problems that combine features of linear-regression-style continuous in-context learning (ICL) with discrete associative recall. We pretrain transf…

cs.IT2026

The Entropy of Floating-Point Numbers

Sultan Daniels, Samuel H. D'Ambrosia, Michael R. DeWeese +1

Here we present an analytic approximation for the entropy of floating-point numbers, along with bounds on the error of this approximation. It is well-known that the differential en…

cs.AI2025

Synthetic Error Injection Fails to Elicit Self-Correction In Language Models

David X. Wu, Shreyas Kapur, Anant Sahai +1

Reinforcement learning has become the dominant paradigm for eliciting reasoning and self-correction capabilities in large language models, but its computational expense motivates e…

cs.LG2025

Precise Asymptotic Generalization for Multiclass Classification with Overparameterized Linear Models

David X. Wu, Anant Sahai

We study the asymptotic generalization of an overparameterized linear model for multiclass classification under the Gaussian covariates bi-level model introduced in Subramanian et…

cs.LG2025

Provable Weak-to-Strong Generalization via Benign Overfitting

David X. Wu, Anant Sahai

The classic teacher-student model in machine learning posits that a strong teacher supervises a weak student to improve the student's capabilities. We instead consider the inverted…