Alexander B. Atanasov

According to our database, Alexander B. Atanasov authored at least 10 papers between 2017 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models.

Alexander B. Atanasov, Blake Bordelon, Jacob A. Zavatone-Veth, Courtney Paquette, Cengiz Pehlevan

CoRR, February, 2025

How Feature Learning Can Improve Neural Scaling Laws.

Blake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

The Optimization Landscape of SGD Across the Feature Learning Strength.

Alexander B. Atanasov, Alexandru Meterez, James B. Simon, Cengiz Pehlevan

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Risk and cross validation in ridge regression with correlated samples.

Alexander B. Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan

CoRR, 2024

Scaling and renormalization in high-dimensional regression.

Alexander B. Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan

CoRR, 2024

A Dynamical Model of Neural Scaling Laws.

Blake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Feature-Learning Networks Are Consistent Across Widths At Realistic Scales.

Nikhil Vyas, Alexander B. Atanasov, Blake Bordelon, Depen Morwani, Sabarish Sainathan, Cengiz Pehlevan

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

Alexander B. Atanasov, Blake Bordelon, Sabarish Sainathan, Cengiz Pehlevan

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Neural Networks as Kernel Learners: The Silent Alignment Effect.

Alexander B. Atanasov, Blake Bordelon, Cengiz Pehlevan

Proceedings of the Tenth International Conference on Learning Representations, 2022

2017

Sparse Grid Discretizations based on a Discontinuous Galerkin Method.

Alexander B. Atanasov, Erik Schnetter

CoRR, 2017