Ezra Winston

6 papers · 2019–2024 · 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 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird

Venues

ICLR (2) ICML (2) NeurIPS (2)

Top co-authors

Stefani Karp (2) Yuanzhi Li (2) Aarti Singh (2) Zachary Lipton (1) Aakash Lahoti (1) Divyansh Kaushik (1) Pradeep Ravikumar (1) Zico Kolter (1) Elan Rosenfeld (1) Chirag Pabbaraju (1)

Research topics

Machine Learning (6) Optimization & Theory · Machine Learning (5) Deep Learning (4) Architectures (4) Application Areas (2) Core Methods (1) Optimization & Theory · Deep Learning (1)

Keywords

convolutional neural network (2) neural network (2) image classification (2) certified robustness (1) data poisoning (1) domain adaptation (1) sample complexity (1) adversarial classification (1) label shift (1) weight sharing (1) generalization bound (1) pac-bayes bound (1) randomized smoothing (1) fixed point (1) distribution alignment (1) monotone operator (1) translation invariance (1) sparse signal (1) lipchitz constant (1) deep equilibrium (1)

Papers

Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs ICLR 2024 Estimating Lipschitz constants of monotone deep equilibrium models ICLR 2021 Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels NeurIPS 2021 Certified Robustness to Label-Flipping Attacks via Randomized Smoothing ICML 2020 Monotone operator equilibrium networks NeurIPS 2020 Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment ICML 2019