Atanasov, Alexander

7 publications

ICLR 2025 How Feature Learning Can Improve Neural Scaling Laws Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan
ICML 2025 Risk and Cross Validation in Ridge Regression with Correlated Samples Alexander Atanasov, Jacob A Zavatone-Veth, Cengiz Pehlevan
ICLR 2025 The Optimization Landscape of SGD Across the Feature Learning Strength Alexander Atanasov, Alexandru Meterez, James B Simon, Cengiz Pehlevan
ICML 2024 A Dynamical Model of Neural Scaling Laws Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan
NeurIPS 2023 Feature-Learning Networks Are Consistent Across Widths at Realistic Scales Nikhil Vyas, Alexander Atanasov, Blake Bordelon, Depen Morwani, Sabarish Sainathan, Cengiz Pehlevan
ICLR 2023 The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes Alexander Atanasov, Blake Bordelon, Sabarish Sainathan, Cengiz Pehlevan
ICLR 2022 Neural Networks as Kernel Learners: The Silent Alignment Effect Alexander Atanasov, Blake Bordelon, Cengiz Pehlevan