Puqian Wang

6 papers · 2023–2025 · 3 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

COLT (2) ICML (2) NeurIPS (2)

Top co-authors

Jelena Diakonikolas (6) Ilias Diakonikolas (6) Nikos Zarifis (6) Daniel M. Kane (1) Daniel Kane (1)

Research topics

Machine Learning (6) Optimization & Theory · Machine Learning (6) Core Methods (4) Mathematics & Optimization (3) Mathematics (2) Optimization (2) Deep Learning (1) Learning Types (1) Optimization & Theory · Deep Learning (1) Probability (1)

Keywords

sample complexity (3) learning theory (2) statistical query (2) robust learning (2) gaussian distribution (2) adversarial label noise (2) single-index model (2) constant-factor approximation (2) agnostic model (2) random classification noise (1) monotone link function (1) generalized linear model (1) relu activation (1) single neuron (1) monotone lipschitz activation (1) alignment sharpness (1) margin halfspace (1) local error bound (1) gaussian noise injection (1) l2 loss (1)

Papers

Robustly Learning Monotone Generalized Linear Models via Data Augmentation COLT 2025 Robustly Learning Single-Index Models via Alignment Sharpness ICML 2024 Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models NeurIPS 2024 Information-Computation Tradeoffs for Learning Margin Halfspaces with Random Classification Noise COLT 2023 Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise NeurIPS 2023 Robustly Learning a Single Neuron via Sharpness ICML 2023