Urmăriți
Yu Huang
Yu Huang
University of Pennsylvania
Adresă de e-mail confirmată pe wharton.upenn.edu
Titlu
Citat de
Citat de
Anul
What makes multi-modal learning better than single (provably)
Y Huang, C Du, Z Xue, X Chen, H Zhao, L Huang
Advances in Neural Information Processing Systems 34, 10944-10956, 2021
3082021
Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)
Y Huang, J Lin, C Zhou, H Yang, L Huang
International Conference on Machine Learning, 9226--9259, 2022
1042022
In-context convergence of transformers
Y Huang, Y Cheng, Y Liang
arXiv preprint arXiv:2310.05249, 2023
822023
Accelerating convergence of score-based diffusion models, provably
G Li, Y Huang, T Efimov, Y Wei, Y Chi, Y Chen
arXiv preprint arXiv:2403.03852, 2024
362024
A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
Y Huang, Z Wen, Y Chi, Y Liang
The Thirteenth International Conference on Learning Representations, 2024
12*2024
Provable generalization of overparameterized meta-learning trained with sgd
Y Huang, Y Liang, L Huang
Advances in Neural Information Processing Systems 35, 16563-16576, 2022
112022
In-context learning with representations: Contextual generalization of trained transformers
T Yang, Y Huang, Y Liang, Y Chi
Advances in Neural Information Processing Systems 37, 85867-85898, 2025
72025
Fast computation of optimal transport via entropy-regularized extragradient methods
G Li, Y Chen, Y Huang, Y Chi, HV Poor, Y Chen
arXiv preprint arXiv:2301.13006, 2023
62023
Online Min-max Problems with Non-convexity and Non-stationarity
Y Huang, Y Cheng, Y Liang, L Huang
Transactions on Machine Learning Research, 2023
2*2023
Heavy traffic analysis of approximate max-weight matching algorithms for input-queued switches
Y Huang, L Huang
Performance Evaluation 144, 102143, 2020
2020
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–10