Anant Sahai

5 papers · 2019–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird ❓ The Questioner

Venues

NeurIPS (2) AISTATS (1) ICLR (1) JMLR (1)

Top co-authors

Vignesh Subramanian (2) Vidya Muthukumar (2) David Wu (1) Adhyyan Narang (1) Rahul Arya (1) Mitas Ray (1) David Xing Wu (1) Mikhail Belkin (1) Peter Bartlett (1) Daniel Hsu (1)

Research topics

Machine Learning (5) Optimization & Theory (5) Core Methods (4) Artificial Intelligence (1) Mathematics & Optimization (1) Bayesian & Probabilistic (1) Learning Types (1) Optimization (1)

Keywords

generalization bound (2) linear model (2) multi-class classification (2) generalization error (1) structural risk minimization (1) adversarial setting (1) support vector machine (1) regret bound (1) loss function (1) benign overfitting (1) least square (1) weak-to-strong generalization (1) overparameterized model (1) teacher-student model (1) overparameterized learning (1) online supervised learning (1) model selection (1) contextual tree expert (1) asymptotic analysis (1) gaussian process (1)

Papers

Provable weak-to-strong generalization via benign overfitting ICLR 2025 Precise asymptotic generalization for multiclass classification with overparameterized linear models NeurIPS 2023 Generalization for multiclass classification with overparameterized linear models NeurIPS 2022 Classification vs regression in overparameterized regimes: Does the loss function matter? JMLR 2021 Best of many worlds: Robust model selection for online supervised learning AISTATS 2019