Alexander Atanasov

7 papers · 2022–2025 · 3 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (15)

Conferences

ICLR (4) ICML (2) NIPS (1)

Top co-authors

Cengiz Pehlevan (7) Blake Bordelon (5) Sabarish Sainathan (2) James B Simon (1) Jacob A Zavatone-Veth (1) Nikhil Vyas (1) Depen Morwani (1) Alexandru Meterez (1)

Keywords

representation learning (1) neural network optimization (1) infinite width limit (1) finite width analysis (1)

Papers

How Feature Learning Can Improve Neural Scaling Laws ICLR 2025

The Optimization Landscape of SGD Across the Feature Learning Strength ICLR 2025

Risk and cross validation in ridge regression with correlated samples ICML 2025

A Dynamical Model of Neural Scaling Laws ICML 2024

Feature-Learning Networks Are Consistent Across Widths At Realistic Scales NIPS 2023

The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes ICLR 2023

Neural Networks as Kernel Learners: The Silent Alignment Effect ICLR 2022