| A diffusion theory for deep learning dynamics: Stochastic gradient descent exponentially favors flat minima Z Xie, I Sato, M Sugiyama International Conference on Learning Representations (ICLR 2021), 2021 | 161 | 2021 |
| Dataset Pruning: Reducing Training Data by Examining Generalization Influence S Yang, Z Xie, H Peng, M Xu, M Sun, P Li International Conference on Learning Representations (ICLR 2023), 2023 | 119 | 2023 |
| Adaptive Inertia: Disentangling the effects of adaptive learning rate and momentum Z Xie, X Wang, H Zhang, I Sato, M Sugiyama International Conference on Machine Learning (ICML 2022, Oral), 2022 | 70* | 2022 |
| Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting Z Xie, F He, S Fu, I Sato, D Tao, M Sugiyama Neural Computation 33 (8), 2163–2192, 2021 | 63 | 2021 |
| Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization Z Xie, L Yuan, Z Zhu, M Sugiyama International Conference on Machine Learning (ICML 2021) 139, 11448--11458, 2021 | 38 | 2021 |
| Sparse Double Descent: Where Network Pruning Aggravates Overfitting Z He, Z Xie, Q Zhu, Z Qin International Conference on Machine Learning (ICML 2022), 2022 | 36 | 2022 |
| On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective Z Xie, Z Xu, J Zhang, I Sato, M Sugiyama Neural Information Processing Systems (NeurIPS 2023), 2024 | 34* | 2024 |
| S3IM: Stochastic Structural SIMilarity and Its Unreasonable Effectiveness for Neural Fields Z Xie, X Yang, Y Yang, Q Sun, Y Jiang, H Wang, Y Cai, M Sun International Conference on Computer Vision (ICCV 2023), 2023 | 32 | 2023 |
| Stable weight decay regularization Z Xie, I Sato, M Sugiyama | 31 | 2020 |
| On the power-law spectrum in deep learning: A bridge to protein science Z Xie, QY Tang, Y Cai, M Sun, P Li arXiv preprint arXiv:2201.13011 2, 2022 | 20* | 2022 |
| On the Overlooked Structure of Stochastic Gradients Z Xie, QY Tang, M Sun, P Li Neural Information Processing Systems (NeurIPS 2023), 2024 | 11* | 2024 |
| Not All Noises Are Created Equally: Diffusion Noise Selection and Optimization Z Qi, L Bai, H Xiong, Z Xie arXiv preprint arXiv:2407.14041, 2024 | 10 | 2024 |
| SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior Z Yu, H Wang, J Yang, H Wang, Z Xie, Y Cai, J Cao, Z Ji, M Sun arXiv preprint arXiv:2403.20079, 2024 | 9 | 2024 |
| Alignment of Diffusion Models: Fundamentals, Challenges, and Future B Liu, S Shao, B Li, L Bai, Z Xu, H Xiong, J Kwok, S Helal, Z Xie arXiv preprint arXiv:2409.07253, 2024 | 7 | 2024 |
| Converging paradigms: The synergy of symbolic and connectionist ai in llm-empowered autonomous agents H Xiong, Z Wang, X Li, J Bian, Z Xie, S Mumtaz, A Al-Dulaimi, LE Barnes arXiv preprint arXiv:2407.08516, 2024 | 4 | 2024 |
| Golden noise for diffusion models: A learning framework Z Zhou, S Shao, L Bai, Z Xu, B Han, Z Xie arXiv preprint arXiv:2411.09502, 2024 | 3 | 2024 |
| HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models H Wang, H Wang, J Yang, Z Yu, Z Xie, L Tian, X Xiao, J Jiang, X Liu, ... arXiv preprint arXiv:2401.05870, 2024 | 3 | 2024 |
| Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data X Zhou, X Liu, H Yu, J Wang, Z Xie, J Jiang, X Ji International Conference on Learning Representations (ICLR 2024), 2024 | 3* | 2024 |
| A Quantum-Inspired Ensemble Method and Quantum-Inspired Forest Regressors Z Xie, I Sato Asian Conference on Machine Learning 2017, PMLR 77, 81-96, 2017 | 3 | 2017 |
| IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis S Shao, Z Zhou, L Bai, H Xiong, Z Xie International Conference on Learning Representations (ICLR 2025), 2025 | 1 | 2025 |
Masashi SugiyamaDirector, RIKEN Center for Advanced Intelligence Project / Professor, The University of TokyoE-mail megerősítve itt: k.u-tokyo.ac.jp