Gabriel Mel

4 papers · 2019–2022 · 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 (10) 🐣 Hot Topic Early Bird

Venues

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

Top co-authors

Surya Ganguli (3) Ben Sorscher (2) Malcolm Campbell (1) Aran Nayebi (1) Alexander Attinger (1) Caitlin S Mallory (1) Jeffrey Pennington (1) Samuel Ocko (1) Dan Yamins (1) Kiah Hardcastle (1)

Research topics

Machine Learning (4) Deep Learning (3) Core Methods (3) Optimization & Theory · Machine Learning (3) Artificial Intelligence (2) Architectures (2) Mathematics & Optimization (1) Core AI (1) Learning Paradigms (1) Mathematics (1) Optimization & Theory · Deep Learning (1)

Keywords

grid cell (2) learning theory (1) double descent (1) neural dynamics (1) ridge regression (1) sample complexity (1) model architecture (1) feature correlation (1) high-dimensional regression (1) high-dimensional analysis (1) neural response (1) phase transition (1) recurrent neural network (1) random feature (1) generalization performance (1) symmetry breaking (1) pattern formation (1) task-driven neural network (1) neuroscience modeling (1) representation learning (1)

Papers

Anisotropic Random Feature Regression in High Dimensions ICLR 2022 A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions ICML 2021 Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks NeurIPS 2021 A unified theory for the origin of grid cells through the lens of pattern formation NeurIPS 2019