Liu, Chaoyue

11 publications

NeurIPS 2025 Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks Chaoyue Liu, Han Bi, Like Hui, Xiao Liu

ICML 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

ICLR 2024 Quadratic Models for Understanding Catapult Dynamics of Neural Networks Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

NeurIPS 2023 Aiming Towards the Minimizers: Fast Convergence of SGD for Overparametrized Problems Chaoyue Liu, Dmitriy Drusvyatskiy, Misha Belkin, Damek Davis, Yian Ma

NeurIPSW 2023 SGD Batch Saturation for Training Wide Neural Networks Chaoyue Liu, Dmitriy Drusvyatskiy, Mikhail Belkin, Damek Davis, Yian Ma

NeurIPS 2022 Transition to Linearity of General Neural Networks with Directed Acyclic Graph Architecture Libin Zhu, Chaoyue Liu, Misha Belkin

ICLR 2022 Transition to Linearity of Wide Neural Networks Is an Emerging Property of Assembling Weak Models Chaoyue Liu, Libin Zhu, Misha Belkin

IJCAI 2021 Two-Sided Wasserstein Procrustes Analysis Kun Jin, Chaoyue Liu, Cathy Xia

ICLR 2020 Accelerating SGD with Momentum for Over-Parameterized Learning Chaoyue Liu, Mikhail Belkin

NeurIPS 2020 On the Linearity of Large Non-Linear Models: When and Why the Tangent Kernel Is Constant Chaoyue Liu, Libin Zhu, Misha Belkin

NeurIPS 2016 Clustering with Bregman Divergences: An Asymptotic Analysis Chaoyue Liu, Mikhail Belkin