3 papers
stat.ML2026
Flatness and Generalization: Learning Multi-Index Models with Homogeneous Neural Networks
Harsh Vardhan, Hossein Taheri, Arya Mazumdar
A common heuristic used to explain the generalization of first-order gradient methods on non-convex neural networks is that "flat interpolators generalize well" (Hochreiter and Sch…
cs.LG2026
Improving Selective Classification with Pairwise Queries for Binary Classification
Harsh Vardhan, Sunav Choudhary, Natwar Modani +1
In selective classification, a model predicts the labels of data samples where it is confident, and abstains from predicting labels for samples on which it is not confident. The re…
cs.LG2024
Interpretable Predictive Models for Healthcare via Rational Logistic Regression
Thiti Suttaket, L Vivek Harsha Vardhan, Stanley Kok
The healthcare sector has experienced a rapid accumulation of digital data recently, especially in the form of electronic health records (EHRs). EHRs constitute a precious resource…