Alexander B. Atanasov

17 papers A* 7Journal 10
YearRankTypeTitle / Venue / Authors
2025 A* conf
How Feature Learning Can Improve Neural Scaling Laws.
ICLR
Blake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan
2025 A* conf
Risk and cross validation in ridge regression with correlated samples.
ICML
Alexander B. Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan
2025 A* conf
The Optimization Landscape of SGD Across the Feature Learning Strength.
ICLR
Alexander B. Atanasov, Alexandru Meterez, James B. Simon, Cengiz Pehlevan
2025 J jnl
Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models.
CoRR
Alexander B. Atanasov, Blake Bordelon, Jacob A. Zavatone-Veth, Courtney Paquette, Cengiz Pehlevan
2024 A* conf
A Dynamical Model of Neural Scaling Laws.
ICML
Blake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan
2024 J jnl
A Dynamical Model of Neural Scaling Laws.
CoRR
Blake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan
2024 J jnl
How Feature Learning Can Improve Neural Scaling Laws.
CoRR
Blake Bordelon, Alexander B. Atanasov, Cengiz Pehlevan
2024 J jnl
Risk and cross validation in ridge regression with correlated samples.
CoRR
Alexander B. Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan
2024 J jnl
Scaling and renormalization in high-dimensional regression.
CoRR
Alexander B. Atanasov, Jacob A. Zavatone-Veth, Cengiz Pehlevan
2024 J jnl
The Optimization Landscape of SGD Across the Feature Learning Strength.
CoRR
Alexander B. Atanasov, Alexandru Meterez, James B. Simon, Cengiz Pehlevan
2023 A* conf
Feature-Learning Networks Are Consistent Across Widths At Realistic Scales.
NeurIPS
Nikhil Vyas, Alexander B. Atanasov, Blake Bordelon, Depen Morwani, Sabarish Sainathan, Cengiz Pehlevan
2023 J jnl
Feature-Learning Networks Are Consistent Across Widths At Realistic Scales.
CoRR
Nikhil Vyas, Alexander B. Atanasov, Blake Bordelon, Depen Morwani, Sabarish Sainathan, Cengiz Pehlevan
2023 A* conf
The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes.
ICLR
Alexander B. Atanasov, Blake Bordelon, Sabarish Sainathan, Cengiz Pehlevan
2022 A* conf
Neural Networks as Kernel Learners: The Silent Alignment Effect.
ICLR
Alexander B. Atanasov, Blake Bordelon, Cengiz Pehlevan
2022 J jnl
The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes.
CoRR
Alexander B. Atanasov, Blake Bordelon, Sabarish Sainathan, Cengiz Pehlevan
2021 J jnl
Neural Networks as Kernel Learners: The Silent Alignment Effect.
CoRR
Alexander B. Atanasov, Blake Bordelon, Cengiz Pehlevan
2017 J jnl
Sparse Grid Discretizations based on a Discontinuous Galerkin Method.
CoRR
Alexander B. Atanasov, Erik Schnetter