Blake Bordelon

CoRR, February, 2025

Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer.

[BibT_eX]

[DOI]

CoRR, February, 2025

2024

Scaling Laws for Precision.

[BibT_eX]

[DOI]

CoRR, 2024

Do Mice Grok? Glimpses of Hidden Progress During Overtraining in Sensory Cortex.

[BibT_eX]

[DOI]

CoRR, 2024

How Feature Learning Can Improve Neural Scaling Laws.

[BibT_eX]

[DOI]

CoRR, 2024

Infinite Limits of Multi-head Transformer Dynamics.

[BibT_eX]

[DOI]

Hamza Tahir Chaudhry

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

A Dynamical Model of Neural Scaling Laws.

[BibT_eX]

[DOI]

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

Grokking as the transition from lazy to rich training dynamics.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Dynamics of Temporal Difference Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks.

[BibT_eX]

[DOI]

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

Loss Dynamics of Temporal Difference Reinforcement Learning.

[BibT_eX]

[DOI]

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

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

[BibT_eX]

[DOI]

Nikhil Vyas

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

The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

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

[BibT_eX]

[DOI]

Sabarish Sainathan

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Learning Curves for SGD on Structured Features.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Neural Networks as Kernel Learners: The Silent Alignment Effect.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Rapid Feature Evolution Accelerates Learning in Neural Networks.

[BibT_eX]

[DOI]

Haozhe Shan

CoRR, 2021

Efficient online inference for nonparametric mixture models.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

Out-of-Distribution Generalization in Kernel Regression.

[BibT_eX]

[DOI]

Abdulkadir Canatar

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Statistical Mechanics of Generalization in Kernel Regression.

[BibT_eX]

[DOI]

Abdulkadir Canatar

CoRR, 2020

Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks.

[BibT_eX]

[DOI]

Abdulkadir Canatar