Loss landscapes and optimization in over-parameterized non-linear systems and neural networks C Liu, L Zhu, M Belkin Applied and Computational Harmonic Analysis 59, 85-116, 2022 | 211 | 2022 |
On the linearity of large non-linear models: when and why the tangent kernel is constant C Liu, L Zhu, M Belkin Advances in Neural Information Processing Systems 33, 15954-15964, 2020 | 156 | 2020 |
Accelerating sgd with momentum for over-parameterized learning C Liu, M Belkin International Conference on Learning Representations, 2020 | 110* | 2020 |
Toward a theory of optimization for over-parameterized systems of non-linear equations: the lessons of deep learning C Liu, L Zhu, M Belkin arXiv preprint arXiv:2003.00307 7, 2020 | 87 | 2020 |
Clustering with Bregman divergences: an asymptotic analysis C Liu, M Belkin Advances in neural information processing systems 29, 2016 | 18 | 2016 |
Quadratic models for understanding catapult dynamics of neural networks L Zhu, C Liu, A Radhakrishnan, M Belkin The Twelfth International Conference on Learning Representations, 0 | 18* | |
Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning L Zhu, C Liu, A Radhakrishnan, M Belkin arXiv preprint arXiv:2306.04815, 2023 | 8 | 2023 |
Aiming towards the minimizers: fast convergence of SGD for overparametrized problems C Liu, D Drusvyatskiy, M Belkin, D Davis, YA Ma Conference on Neural Information Processing Systems (NIPS), 2023 | 6 | 2023 |
Transition to linearity of general neural networks with directed acyclic graph architecture L Zhu, C Liu, M Belkin Advances in neural information processing systems 35, 5363-5375, 2022 | 6 | 2022 |
Two-Sided Wasserstein Procrustes Analysis. K Jin, C Liu, C Xia IJCAI, 3515-3521, 2021 | 5 | 2021 |
Parametrized accelerated methods free of condition number C Liu, M Belkin arXiv preprint arXiv:1802.10235, 2018 | 5 | 2018 |
Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models C Liu, L Zhu, M Belkin International Conference on Learning Representations, 2022 | 4 | 2022 |
On emergence of clean-priority learning in early stopped neural networks C Liu, A Abedsoltan, M Belkin arXiv preprint arXiv:2306.02533, 2023 | 2 | 2023 |
ReLU soothes the NTK condition number and accelerates optimization for wide neural networks C Liu, L Hui arXiv preprint arXiv:2305.08813, 2023 | 2 | 2023 |
Otda: a unsupervised optimal transport framework with discriminant analysis for keystroke inference K Jin, C Liu, C Xia 2020 IEEE Conference on Communications and Network Security (CNS), 1-9, 2020 | 1 | 2020 |
Understanding and Accelerating the Optimization of Modern Machine Learning C Liu The Ohio State University, 2021 | | 2021 |
SGD batch saturation for training wide neural networks C Liu, D Drusvyatskiy, M Belkin, D Davis, Y Ma | | |