Chaoyue Liu

According to our database, Chaoyue Liu authored at least 18 papers between 2016 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2024

Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning.

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

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

Quadratic models for understanding catapult dynamics of neural networks.

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Aiming towards the minimizers: fast convergence of SGD for overparametrized problems.

Chaoyue Liu, Dmitriy Drusvyatskiy, Mikhail Belkin, Damek Davis, Yi-An Ma

CoRR, 2023

On Emergence of Clean-Priority Learning in Early Stopped Neural Networks.

Chaoyue Liu, Amirhesam Abedsoltan, Mikhail Belkin

CoRR, 2023

Aiming towards the minimizers: fast convergence of SGD for overparametrized problems.

Chaoyue Liu, Dmitriy Drusvyatskiy, Misha Belkin, Damek Davis, Yi-An Ma

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

2022

Quadratic models for understanding neural network dynamics.

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

CoRR, 2022

Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture.

Libin Zhu, Chaoyue Liu, Mikhail Belkin

CoRR, 2022

Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models.

Chaoyue Liu, Libin Zhu, Mikhail Belkin

CoRR, 2022

Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture.

Libin Zhu, Chaoyue Liu, Misha Belkin

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

Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models.

Chaoyue Liu, Libin Zhu, Misha Belkin

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Two-Sided Wasserstein Procrustes Analysis.

Kun Jin, Chaoyue Liu, Cathy Xia

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

2020

Toward a theory of optimization for over-parameterized systems of non-linear equations: the lessons of deep learning.

Chaoyue Liu, Libin Zhu, Mikhail Belkin

CoRR, 2020

On the linearity of large non-linear models: when and why the tangent kernel is constant.

Chaoyue Liu, Libin Zhu, Mikhail Belkin

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

Accelerating SGD with momentum for over-parameterized learning.

Chaoyue Liu, Mikhail Belkin

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

OTDA: a Unsupervised Optimal Transport framework with Discriminant Analysis for Keystroke Inference.

Kun Jin, Chaoyue Liu, Cathy Xia

Proceedings of the 8th IEEE Conference on Communications and Network Security, 2020

2018

MaSS: an Accelerated Stochastic Method for Over-parametrized Learning.

Chaoyue Liu, Mikhail Belkin

CoRR, 2018

Parametrized Accelerated Methods Free of Condition Number.

Chaoyue Liu, Mikhail Belkin

CoRR, 2018

2016

Clustering with Bregman Divergences: an Asymptotic Analysis.

Chaoyue Liu, Mikhail Belkin

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016