Theodor Misiakiewicz

CoRR, 2024

A non-asymptotic theory of Kernel Ridge Regression: deterministic equivalents, test error, and GCV estimator.

[BibT_eX]

[DOI]

Basil Saeed

CoRR, 2024

Asymptotics of Random Feature Regression Beyond the Linear Scaling Regime.

[BibT_eX]

[DOI]

Hong Hu

Yue M. Lu

CoRR, 2024

On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries.

[BibT_eX]

[DOI]

Nirmit Joshi

Nati Srebro

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

Dimension-free deterministic equivalents and scaling laws for random feature regression.

[BibT_eX]

[DOI]

Leonardo Defilippis

Bruno Loureiro

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

2023

Six Lectures on Linearized Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2023

SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics.

[BibT_eX]

[DOI]

Emmanuel Abbe

Enric Boix Adserà

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Precise Learning Curves and Higher-Order Scalings for Dot-product Kernel Regression.

[BibT_eX]

[DOI]

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

Learning with convolution and pooling operations in kernel methods.

[BibT_eX]

[DOI]

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

The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks.

[BibT_eX]

[DOI]

Emmanuel Abbe

Enric Boix Adserà

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

Minimum complexity interpolation in random features models.

[BibT_eX]

[DOI]

Michael Celentano

CoRR, 2021

Learning with invariances in random features and kernel models.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

2020

When Do Neural Networks Outperform Kernel Methods?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Limitations of Lazy Training of Two-layers Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2019

Linearized two-layers neural networks in high dimension.

[BibT_eX]

[DOI]

CoRR, 2019

Limitations of Lazy Training of Two-layers Neural Network.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2019

2017

Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality.

[BibT_eX]

[DOI]

Roberto Imbuzeiro Oliveira

Proceedings of the 30th Conference on Learning Theory, 2017

2015

Efficient reconstruction of transmission probabilities in a spreading process from partial observations.

[BibT_eX]

[DOI]

Andrey Y. Lokhov

CoRR, 2015

Concentration to zero bit-error probability for regular LDPC codes on the binary symmetric channel: Proof by loop calculus.

[BibT_eX]

[DOI]

Marc Vuffray