| Think locally, act globally: Federated learning with local and global representations PP Liang, T Liu, L Ziyin, NB Allen, RP Auerbach, D Brent, ... NeurIPS 2019 Federated Learning Workshop, 2020 | 527 | 2020 |
| Multimodal language analysis with recurrent multistage fusion PP Liang, Z Liu, A Zadeh, LP Morency EMNLP 2018 Oral, 2018 | 210 | 2018 |
| Deep gamblers: Learning to abstain with portfolio theory Z Liu, Z Wang, PP Liang, RR Salakhutdinov, LP Morency, M Ueda Advances in Neural Information Processing Systems 32, 2019 | 121 | 2019 |
| Neural networks fail to learn periodic functions and how to fix it L Ziyin, T Hartwig, M Ueda Advances in Neural Information Processing Systems 33, 1583-1594, 2020 | 103 | 2020 |
| Strength of minibatch noise in SGD L Ziyin, K Liu, T Mori, M Ueda ICLR 2022 Spotlight, 2021 | 41* | 2021 |
| Noise and fluctuation of finite learning rate stochastic gradient descent K Liu, L Ziyin, M Ueda International Conference on Machine Learning, 7045-7056, 2021 | 31* | 2021 |
| Sgd can converge to local maxima L Ziyin, B Li, JB Simon, M Ueda International Conference on Learning Representations Spotlight, 2021 | 29* | 2021 |
| Cross-modal generalization: Learning in low resource modalities via meta-alignment PP Liang, P Wu, L Ziyin, LP Morency, R Salakhutdinov Proceedings of the 29th ACM International Conference on Multimedia, 2680-2689, 2021 | 27 | 2021 |
| Power-law escape rate of SGD T Mori, L Ziyin, K Liu, M Ueda International Conference on Machine Learning, 15959-15975, 2022 | 24 | 2022 |
| Posterior collapse of a linear latent variable model Z Wang, L Ziyin Advances in Neural Information Processing Systems 35, 37537-37548, 2022 | 21 | 2022 |
| Learning not to learn in the presence of noisy labels L Ziyin, B Chen, R Wang, PP Liang, R Salakhutdinov, LP Morency, ... arXiv preprint arXiv:2002.06541, 2020 | 20 | 2020 |
| On the stepwise nature of self-supervised learning JB Simon, M Knutins, L Ziyin, D Geisz, AJ Fetterman, J Albrecht International Conference on Machine Learning, 31852-31876, 2023 | 19 | 2023 |
| An investigation of how label smoothing affects generalization B Chen, L Ziyin, Z Wang, PP Liang arXiv preprint arXiv:2010.12648, 2020 | 19 | 2020 |
| LaProp: Separating momentum and adaptivity in adam L Ziyin, ZT Wang, M Ueda arXiv preprint arXiv:2002.04839, 2020 | 19* | 2020 |
| What shapes the loss landscape of self-supervised learning? L Ziyin, ES Lubana, M Ueda, H Tanaka arXiv preprint arXiv:2210.00638, 2022 | 18 | 2022 |
| Exact solutions of a deep linear network L Ziyin, B Li, X Meng Advances in Neural Information Processing Systems 35, 24446-24458, 2022 | 13 | 2022 |
| Zeroth, first, and second-order phase transitions in deep neural networks L Ziyin, M Ueda Physical Review Research 5 (4), 043243, 2023 | 11* | 2023 |
| spred: Solving L1 Penalty with SGD L Ziyin, Z Wang International Conference on Machine Learning, 43407-43422, 2023 | 8* | 2023 |
| The probabilistic stability of stochastic gradient descent L Ziyin, B Li, T Galanti, M Ueda arXiv preprint arXiv:2303.13093, 2023 | 8 | 2023 |
| Law of balance and stationary distribution of stochastic gradient descent L Ziyin, H Li, M Ueda arXiv preprint arXiv:2308.06671, 2023 | 7 | 2023 |
