Selected Publications

* indicates equal contributions. Full list refers to Google Scholar
Conference
A Han, W Huang, Y Cao, D Zou.
On the Feature Learning in Diffusion Models.
In International Conference on Learning Representations (ICLR 2025).
[Paper]
B Li, W Huang, A Han, Z Zhou, T Suzuki, J Zhu, J Chen.
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent.
In International Conference on Learning Representations (ICLR 2025 Spotlight).
[Paper]
D Shi, L Lin, A Han, Z Wang, Y Guo, J Gao.
When Graph Neural Networks Meet Dynamic Mode Decomposition.
In International Conference on Learning Representations (ICLR 2025).
[Paper]
L Lin, D Shi, A Han, Z Wang, J Gao.
Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning.
In International Conference on Learning Representations (ICLR 2025).
[Paper]
Y Hu*, Y Tan*, A Han*, L Zheng, L Hong, B Zhou.
Secondary Structure-Guided Novel Protein Sequence Generation with Latent Graph Diffusion.
In IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM 2024) + International Conference on Machine Learning AI for Science Workshop(ICML 2024 AI4Science).
[Paper] [Code]
A Han, J Li, W Huang, M Hong, A Takeda, P Jawanpuria, B Mishra.
SLTrain: a Sparse Plus Low Rank Approach for Parameter and Memory Efficient Pretraining.
In Advances in Neural Information Processing Systems (NeurIPS 2024).
[Paper] [Code]
A Han, B Mishra, P Jawanpuria, A Takeda.
A Framework for Bilevel Optimization on Riemannian Manifolds.
In Advances in Neural Information Processing Systems (NeurIPS 2024).
[Paper] [Code]
W Huang*, A Han*, Y Chen, Y Cao, Z Xu, T Suzuki.
On the Comparison between Multi-modal and Single-modal Contrastive Learning.
In Advances in Neural Information Processing Systems (NeurIPS 2024).
[Paper]
D Bu, W Huang, A Han, A Nitanda, T Suzuki, Q Zhang, H Wong.
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning.
In Advances in Neural Information Processing Systems (NeurIPS 2024).
[Paper]
A Han, P Jawanpuria, B Mishra.
Riemannian Coordinate Descent Algorithms on Matrix Manifolds.
In International Conference on Machine Learning (ICML 2024).
[Paper] [Code]
A Han, B Mishra, P Jawanpuria, J Gao.
Riemannian Accelerated Gradient Methods via Extrapolation.
In International Conference on Artificial Intelligence and Statistics (AISTATS 2023).
[Paper] [Code]
A Han, B Mishra, P Jawanpuria, J Gao.
On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry.
In Advances in Neural Information Processing Systems (NeurIPS 2021).
[Paper] [Code]
Journal
A Han, B Mishra, P Jawanpuria, P Kumar, J Gao.
Riemannian Hamiltonian Methods for Min-max Optimization on Manifolds.
SIAM Journal on Optimization.
[Paper] [Code]
A Han, J Gao.
Improved Variance Reduction Methods for Riemannian Non-convex Optimization.
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[Paper] [Code]
A Han, B Mishra, P Jawanpuria, J Gao.
Differentially Private Riemannian Optimization.
Machine Learning (ECML 2023 Special Issue).
[Paper] [Code]
A Han, D Shi, L Lin, J Gao.
From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyond.
Transactions on Machine Learning Research.
[Paper]
Book Chapter and Thesis
A Han, P Jawanpuria, and B Mishra. Riemannian Optimization. Encyclopedia of Optimization. 2024. [Link]
A Han. Optimization and Learning over Riemannian Manifolds. USYD Doctoral Thesis. 2023. [PDF]

Talks

Invited talk on Leveraging low rank and sparsity for efficient pretraining, @Zhejiang Lab (Oct. 2024)
Invited talk on Subspace methods for efficient optimization on matrix manifolds, @USYD (May. 2024)
Invited talk on Optimization on smooth manifolds and its applications, @CUHK (Feb. 2024)

Professional Service

Conference reviewer: NeurIPS, ICML, ICLR, AISTATS, AAAI, IJCAI, IJCNN
Journal reviewer: JMLR, ML (Springer), SICON, TMLR, FITEE, Symmetry

Honors and Awards