| Scalable and efficient training of large convolutional neural networks with differential privacy Z Bu, J Mao, S Xu Advances in Neural Information Processing Systems 35, 38305-38318, 2022 | 64 | 2022 |
| Saliency-based sequential image attention with multiset prediction S Welleck, J Mao, K Cho, Z Zhang Advances in neural information processing systems 30, 2017 | 27 | 2017 |
| Does the data induce capacity control in deep learning? R Yang, J Mao, P Chaudhari International Conference on Machine Learning, 25166-25197, 2022 | 23 | 2022 |
| Loss functions for multiset prediction S Welleck, Z Yao, Y Gai, J Mao, Z Zhang, K Cho Advances in Neural Information Processing Systems 31, 2018 | 23 | 2018 |
| The training process of many deep networks explores the same low-dimensional manifold J Mao, I Griniasty, HK Teoh, R Ramesh, R Yang, MK Transtrum, ... Proceedings of the National Academy of Sciences 121 (12), e2310002121, 2024 | 17 | 2024 |
| A picture of the space of typical learnable tasks R Ramesh, J Mao, I Griniasty, R Yang, HK Teoh, M Transtrum, JP Sethna, ... International Conference on Machine Learning (ICML 23), 2022 | 6 | 2022 |
| A Picture of the Prediction Space of Deep Networks J Mao, I Griniasty, R Yang, HK Teoh, R Ramesh, M Transtrum, J Sethna, ... APS March Meeting Abstracts 2023, B12. 003, 2023 | | 2023 |
| The Role of Data in the Sloppiness of Deep Networks P Chaudhari, R Yang, J Mao APS March Meeting Abstracts 2022, F09. 004, 2022 | | 2022 |
