Yu Huang

Affiliations:

Tsinghua University, Institute for Interdisciplinary Information Sciences, IIIS, China

According to our database¹, Yu Huang authored at least 13 papers between 2020 and 2025.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2025

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent.

[BibT_eX]

[DOI]

CoRR, August, 2025

Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods.

[BibT_eX]

[DOI]

SIAM J. Optim., 2025

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

Transformers Provably Learn Feature-Position Correlations in Masked Image Modeling.

[BibT_eX]

[DOI]

CoRR, 2024

In-Context Learning with Representations: Contextual Generalization of Trained Transformers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

In-context Convergence of Transformers.

[BibT_eX]

[DOI]

Yu Huang

Yuan Cheng

Yingbin Liang

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Accelerating Convergence of Score-Based Diffusion Models, Provably.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Online Min-max Problems with Non-convexity and Non-stationarity.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2023

2022

Provable Generalization of Overparameterized Meta-learning Trained with SGD.

[BibT_eX]

[DOI]

Yu Huang

Yingbin Liang

Longbo Huang

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably).

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

2021

What Makes Multimodal Learning Better than Single (Provably).

[BibT_eX]

[DOI]

CoRR, 2021

What Makes Multi-Modal Learning Better than Single (Provably).

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Heavy traffic analysis of approximate max-weight matching algorithms for input-queued switches.

[BibT_eX]

[DOI]

Yu Huang

Longbo Huang

Perform. Evaluation, 2020

Yu Huang

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...