Greg Ongie

6 papers · 2017–2025 · 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 🗺️ Taxonomy Completionist (11) ❓ The Questioner

Venues

ICLR (2) ICML (2) COLT (1) NeurIPS (1)

Top co-authors

Daniel Soudry (4) Rebecca Willett (3) Tomer Michaeli (2) Nir Weinberger (2) Chen Zeno (2) Nathan Srebro (2) Suzanna Parkinson (1) Robert D. Nowak (1) Rotem Mulayoff (1) Laura Balzano (1)

Research topics

Deep Learning (5) Machine Learning (4) Architectures (4) Optimization & Theory · Machine Learning (4) Computer Vision (1) Mathematics & Optimization (1) Mathematics (1) Models (1) Optimization & Theory · Deep Learning (1) Processing (1)

Keywords

relu network (3) function space (2) stochastic gradient descent (1) sample complexity (1) deep learning (1) multivariate analysis (1) matrix completion (1) low-rank matrix (1) minimum norm (1) implicit bia (1) polynomial equation (1) infinite width (1) kernel trick (1) universal approximator (1) rectified linear unit (1) weight norm (1) probability flow (1) infinite-width neural network (1) neural network (1) interpolation method (1)

Papers

When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets ICML 2025 Depth Separation in Norm-Bounded Infinite-Width Neural Networks COLT 2024 How do Minimum-Norm Shallow Denoisers Look in Function Space? NeurIPS 2023 The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks ICLR 2023 A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case ICLR 2020 Algebraic Variety Models for High-Rank Matrix Completion ICML 2017