Boris Hanin

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

Collaborative distances:

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

2024

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

Jared Quincy Davis, Boris Hanin, Lingjiao Chen, Peter Bailis, Ion Stoica, Matei Zaharia

CoRR, 2024

Bayesian Inference with Deep Weakly Nonlinear Networks.

Boris Hanin, Alexander Zlokapa

CoRR, 2024

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

Lingjiao Chen, Jared Quincy Davis, Boris Hanin, Peter Bailis, Ion Stoica, Matei Zaharia, James Zou

CoRR, 2024

Principled Architecture-aware Scaling of Hyperparameters.

Wuyang Chen, Junru Wu, Zhangyang Wang, Boris Hanin

Proceedings of the Twelfth International Conference on Learning Representations, 2024

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

Blake Bordelon, Lorenzo Noci, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

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

Yasaman Bahri, Boris Hanin, Antonin Brossollet, Vittorio Erba, Christian Keup, Rosalba Pacelli, James B. Simon

CoRR, 2023

Quantitative CLTs in Deep Neural Networks.

Stefano Favaro, Boris Hanin, Domenico Marinucci, Ivan Nourdin, Giovanni Peccati

CoRR, 2023

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

Gage DeZoort, Boris Hanin

CoRR, 2023

Depth Dependence of μP Learning Rates in ReLU MLPs.

Samy Jelassi, Boris Hanin, Ziwei Ji, Sashank J. Reddi, Srinadh Bhojanapalli, Sanjiv Kumar

CoRR, 2023

Maximal Initial Learning Rates in Deep ReLU Networks.

Gaurav Iyer, Boris Hanin, David Rolnick

Proceedings of the International Conference on Machine Learning, 2023

2022

Bayesian Interpolation with Deep Linear Networks.

Boris Hanin, Alexander Zlokapa

CoRR, 2022

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

Boris Hanin

CoRR, 2022

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis.

Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang

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.

Boris Hanin, Ryan S. Jeong, David Rolnick

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Neural network approximation.

Ronald A. DeVore, Boris Hanin, Guergana Petrova

Acta Numer., May, 2021

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

Boris Hanin

CoRR, 2021

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

Boris Hanin

CoRR, 2021

The Principles of Deep Learning Theory.

Daniel A. Roberts, Sho Yaida, Boris Hanin

CoRR, 2021

How Data Augmentation affects Optimization for Linear Regression.

Boris Hanin, Yi Sun

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.

Boris Hanin, Yi Sun

CoRR, 2020

Finite Depth and Width Corrections to the Neural Tangent Kernel.

Boris Hanin, Mihai Nica

Proceedings of the 8th International Conference on Learning Representations, 2020

2019

Nonlinear Approximation and (Deep) ReLU Networks.

Ingrid Daubechies, Ronald A. DeVore, Simon Foucart, Boris Hanin, Guergana Petrova

CoRR, 2019

Deep ReLU Networks Have Surprisingly Few Activation Patterns.

Boris Hanin, David Rolnick

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.

Boris Hanin, David Rolnick

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

How to Start Training: The Effect of Initialization and Architecture.

Boris Hanin, David Rolnick

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?

Boris Hanin

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.

Boris Hanin, Mark Sellke

CoRR, 2017

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

Boris Hanin

CoRR, 2017