Boris Hanin

According to our database1, Boris Hanin authored at least 28 papers between 2017 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Networks of Networks: Complexity Class Principles Applied to Compound AI Systems Design.
CoRR, 2024

Bayesian Inference with Deep Weakly Nonlinear Networks.
CoRR, 2024

Are More LLM Calls All You Need? Towards Scaling Laws of Compound Inference Systems.
CoRR, 2024

Principled Architecture-aware Scaling of Hyperparameters.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023
Les Houches Lectures on Deep Learning at Large & Infinite Width.
CoRR, 2023

Quantitative CLTs in Deep Neural Networks.
CoRR, 2023

Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations.
CoRR, 2023

Depth Dependence of μP Learning Rates in ReLU MLPs.
CoRR, 2023

Maximal Initial Learning Rates in Deep ReLU Networks.
Proceedings of the International Conference on Machine Learning, 2023

2022
Bayesian Interpolation with Deep Linear Networks.
CoRR, 2022

Correlation Functions in Random Fully Connected Neural Networks at Finite Width.
CoRR, 2022

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Deep ReLU Networks Preserve Expected Length.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Neural network approximation.
Acta Numer., May, 2021

Ridgeless Interpolation with Shallow ReLU Networks in $1D$ is Nearest Neighbor Curvature Extrapolation and Provably Generalizes on Lipschitz Functions.
CoRR, 2021

Random Neural Networks in the Infinite Width Limit as Gaussian Processes.
CoRR, 2021

The Principles of Deep Learning Theory.
CoRR, 2021

How Data Augmentation affects Optimization for Linear Regression.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020
Data augmentation as stochastic optimization.
CoRR, 2020

Finite Depth and Width Corrections to the Neural Tangent Kernel.
Proceedings of the 8th International Conference on Learning Representations, 2020

2019
Nonlinear Approximation and (Deep) ReLU Networks.
CoRR, 2019

Deep ReLU Networks Have Surprisingly Few Activation Patterns.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Complexity of Linear Regions in Deep Networks.
Proceedings of the 36th International Conference on Machine Learning, 2019

2018
How to Start Training: The Effect of Initialization and Architecture.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients?
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2017
Approximating Continuous Functions by ReLU Nets of Minimal Width.
CoRR, 2017

Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations.
CoRR, 2017


  Loading...