6 papers
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 …
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…
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…
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…
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…
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…