Blake Bordelon

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 32

Top Topics

Temporal Difference

Learning Curves

Reinforcement Learning

Top Venues

Publications

Blake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit. ICLR (2024)
Blake Bordelon, Hamza Tahir Chaudhry, Cengiz Pehlevan
Infinite Limits of Multi-head Transformer Dynamics. CoRR (2024)
Tanishq Kumar, Blake Bordelon, Samuel J. Gershman, Cengiz Pehlevan
Grokking as the transition from lazy to rich training dynamics. ICLR (2024)
Blake Bordelon, Alexander Atanasov, Cengiz Pehlevan
A Dynamical Model of Neural Scaling Laws. CoRR (2024)
Blake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit. CoRR (2023)
Blake Bordelon, Paul Masset, Henry Kuo, Cengiz Pehlevan
Loss Dynamics of Temporal Difference Reinforcement Learning. NeurIPS (2023)
Nikhil Vyas, Alexander Atanasov, Blake Bordelon, Depen Morwani, Sabarish Sainathan, Cengiz Pehlevan
Feature-Learning Networks Are Consistent Across Widths At Realistic Scales. CoRR (2023)
Blake Bordelon, Cengiz Pehlevan
Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks. NeurIPS (2023)
Blake Bordelon, Paul Masset, Henry Kuo, Cengiz Pehlevan
Dynamics of Temporal Difference Reinforcement Learning. CoRR (2023)
Alexander Atanasov, Blake Bordelon, Sabarish Sainathan, Cengiz Pehlevan
The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes. ICLR (2023)
Nikhil Vyas, Alexander Atanasov, Blake Bordelon, Depen Morwani, Sabarish Sainathan, Cengiz Pehlevan
Feature-Learning Networks Are Consistent Across Widths At Realistic Scales. NeurIPS (2023)
Blake Bordelon, Cengiz Pehlevan
Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks. CoRR (2023)
Blake Bordelon, Cengiz Pehlevan
The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks. ICLR (2023)
Tanishq Kumar, Blake Bordelon, Samuel J. Gershman, Cengiz Pehlevan
Grokking as the Transition from Lazy to Rich Training Dynamics. CoRR (2023)
Blake Bordelon, Cengiz Pehlevan
The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks. CoRR (2022)
Matthew Farrell, Blake Bordelon, Shubhendu Trivedi, Cengiz Pehlevan
Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views? ICLR (2022)
Alexander Atanasov, Blake Bordelon, Sabarish Sainathan, Cengiz Pehlevan
The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes. CoRR (2022)
Blake Bordelon, Cengiz Pehlevan
Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks. NeurIPS (2022)
Blake Bordelon, Cengiz Pehlevan
Learning Curves for SGD on Structured Features. ICLR (2022)
Alexander Atanasov, Blake Bordelon, Cengiz Pehlevan
Neural Networks as Kernel Learners: The Silent Alignment Effect. ICLR (2022)
Blake Bordelon, Cengiz Pehlevan
Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks. CoRR (2022)
Rylan Schaeffer, Blake Bordelon, Mikail Khona, Weiwei Pan, Ila Rani Fiete
Efficient online inference for nonparametric mixture models. UAI (2021)
Abdulkadir Canatar, Blake Bordelon, Cengiz Pehlevan
Out-of-Distribution Generalization in Kernel Regression. CoRR (2021)
Matthew Farrell, Blake Bordelon, Shubhendu Trivedi, Cengiz Pehlevan
Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views? CoRR (2021)
Haozhe Shan, Blake Bordelon
Rapid Feature Evolution Accelerates Learning in Neural Networks. CoRR (2021)
Alexander Atanasov, Blake Bordelon, Cengiz Pehlevan
Neural Networks as Kernel Learners: The Silent Alignment Effect. CoRR (2021)
Blake Bordelon, Cengiz Pehlevan
Learning Curves for SGD on Structured Features. CoRR (2021)
Abdulkadir Canatar, Blake Bordelon, Cengiz Pehlevan
Out-of-Distribution Generalization in Kernel Regression. NeurIPS (2021)
Abdulkadir Canatar, Blake Bordelon, Cengiz Pehlevan
Statistical Mechanics of Generalization in Kernel Regression. CoRR (2020)
Blake Bordelon, Abdulkadir Canatar, Cengiz Pehlevan
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks. CoRR (2020)
Blake Bordelon, Abdulkadir Canatar, Cengiz Pehlevan
Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks. ICML (2020)
Bryce Bagley, Blake Bordelon, Benjamin Moseley, Ralf Wessel
Pre-Synaptic Pool Modification (PSPM): A Supervised Learning Procedure for Spiking Neural Networks. CoRR (2018)