Tam LE - Publications

Google Scholar Page for a list of my most recent preprints.
(*: equal contribution; ⊛: co-last author)

Selected ML Journals / Conference Papers

• Tree-Sliced Sobolev IPM
  ICLR, 2026.
  Viet-Hoang Tran*, Thanh Q. Tran*, Thanh Chu, Duy-Tung Pham, Trung-Khang Tran, Tam Le⊛, Tan M. Nguyen⊛.

• Revisiting Tree-Sliced Wasserstein Distance through the Lens of the Fermat–Weber Problem
  ICLR, 2026.
  Viet-Hoang Tran*, Thanh Q. Tran*, Thanh Chu*, Trung-Khang Tran, Duy-Tung Pham, Tam Le⊛, Tan M. Nguyen⊛.

• An Efficient Orlicz-Sobolev Approach for Transporting Unbalanced Measures on a Graph [POSTER/SLIDE]
  NeurIPS, 2025. [Spotlight rate: 688/21575=3.19%]
  Tam Le*, Truyen Nguyen*, Hideitsu Hino, Kenji Fukumizu.
  (This paper was selected for a spotlight presentation. Spotlight : acceptance : submissions = 688 : 5290 : 21575)

• Tree-Sliced Entropy Partial Transport. [POSTER]
  NeurIPS, 2025.
  Viet-Hoang Tran, Thanh Tran, Thanh T. Chu, Tam Le⊛, Tan M. Nguyen⊛.

• Tree Structure for the Categorical Wasserstein Weisfeiler-Lehman Graph Kernel
  TMLR, 2025.
  Keishi Sando, Tam Le, Hideitsu Hino.

• Tree-Sliced Wasserstein Distance: A Geometric Perspective. [POSTER]
  ICML, 2025.
  Viet-Hoang Tran*, Trang Pham*, Tho Tran, Khoi N.M. Nguyen, Thanh T. Chu, Tam Le⊛, Tan M. Nguyen⊛.

• Tree-Sliced Wasserstein Distance with Nonlinear Projection. [POSTER]
  ICML, 2025.
  Thanh Tran*, Viet-Hoang Tran*, Thanh T. Chu, Trang Pham, Laurent El Ghaoui⊛, Tam Le⊛, Tan M. Nguyen⊛.

• Scalable Sobolev IPM for Probability Measures on a Graph. [POSTER/SLIDE]
  ICML, 2025.
  Tam Le*, Truyen Nguyen*, Hideitsu Hino, Kenji Fukumizu.

• Distance-Based Tree-Sliced Wasserstein Distance. [POSTER]
  ICLR, 2025.
  Viet-Hoang Tran*, Khoi N.M. Nguyen*, Trang Pham, Thanh T. Chu, Tam Le⊛, Tan M. Nguyen⊛.
  (Preliminary workshop version in ICLR workshop: DeLTa, 2025)

• Spherical Tree-Sliced Wasserstein Distance. [POSTER]
  ICLR, 2025.
  Viet-Hoang Tran*, Thanh T. Chu*, Khoi N.M. Nguyen, Trang Pham, Tam Le⊛, Tan M. Nguyen⊛.
  (Preliminary workshop version in ICLR workshop: DeLTa, 2025)

• SAVA: Scalable Learning-Agnostic Data Valuation. [POSTER]
  ICLR, 2025.
  Samuel Kessler*, Tam Le*, Vu Nguyen.

• Generalized Sobolev Transport for Probability Measures on a Graph. [POSTER/SLIDE]
  ICML, 2024.
  Tam Le*, Truyen Nguyen*, Kenji Fukumizu.

• Sliced Wasserstein with Random-Path Projecting Directions. [POSTER]
  ICML, 2024.
  Khai Nguyen, Shujian Zhang, Tam Le, Nhat Ho.

• Optimal Transport for Measures with Noisy Tree Metric. [POSTER]
  AISTATS, 2024.
  Tam Le, Truyen Nguyen, Kenji Fukumizu.
  (Preliminary workshop version in NeurIPS workshop: OTML, 2023)

• Scalable Unbalanced Sobolev Transport for Measures on a Graph. [POSTER]
  AISTATS, 2023.
  Tam Le*, Truyen Nguyen*, Kenji Fukumizu.

• Sobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics. [Video/Supplementary/POSTER]
  AISTATS, 2022.
  Tam Le*, Truyen Nguyen*, Dinh Phung, Viet Anh Nguyen.

• Adversarial Regression with Doubly Non-negative Weighting Matrices. [Video/Supplementary/SLIDE/POSTER]
  NeurIPS, 2021.
  Tam Le*, Truyen Nguyen*, Makoto Yamada, Jose Blanchet, Viet Anh Nguyen.

• Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search. [Supplementary/POSTER]
  ICML, 2021.
  Vu Nguyen*, Tam Le*, Makoto Yamada, Michael A. Osborne.
  

• Entropy Partial Transport with Tree Metrics: Theory and Practice. [Video/Supplementary/SLIDE/POSTER]
  AISTATS, 2021. [Oral rate: 48/1527=3.14%]
  Tam Le*, Truyen Nguyen*
  (This paper was selected for an oral presentation. Oral : acceptance : submissions = 48 : 455 : 1527)

• Flow-based Alignment Approaches for Probability Measures in Different Spaces. [Video/Supplementary/POSTER]
  AISTATS, 2021.
  Tam Le*, Nhat Ho*, Makoto Yamada.

• Tree-Sliced Variants of Wasserstein Distances. [Supplementary/POSTER]
  NeurIPS, 2019.
  Tam Le, Makoto Yamada, Kenji Fukumizu, Marco Cuturi.

• Safe Grid Search with Optimal Complexity. [Supplementary/POSTER]
  ICML, 2019.
  Eugene Ndiaye, Tam Le, Olivier Fercoq, Joseph Salmon, Ichiro Takeuchi.
  

• Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagrams. [Supplementary/POSTER]
  NeurIPS, 2018.
  Tam Le, Makoto Yamada.
  (Preliminary workshop version in ICML workshop: GML, 2018)

• Unsupervised Riemannian Metric Learning for Histograms Using Aitchison Transformations. [Video/Supplemental/SLIDE/POSTER]
  ICML, 2015.
  Tam Le, Marco Cuturi.
  

• Adaptive Euclidean Maps for Histograms: Generalized Aitchison Embeddings
  ML Journal (MLJ), 2014.
  Tam Le, Marco Cuturi.
  (Preliminary conference version in ACML, 2013)

Others

Other Journals / Conference Papers / Preprints

• Generalized Sobolev IPM for Graph-Based Measures
  ArXiv, 2025.
  Tam Le*, Truyen Nguyen*, Hideitsu Hino, Kenji Fukumizu.

• Few-Shot Object Detection via Synthetic Features with Optimal Transport
  CVIU Journal, 2025.
  Anh-Khoa Nguyen-Vu, Thanh-Toan Do, Vinh-Tiep Nguyen, Tam Le, Minh-Triet Tran, Tam V. Nguyen

• Scalable Counterfactual Distribution Estimation in Multivariate Causal Models. [POSTER]
  CLeaR, 2024.
  Thong Pham, Shohei Shimizu, Hideitsu Hino, Tam Le.

• Dynamic Flows on Curved Space Generated by Labeled Data
  IJCAI, 2023.
  Xinru Hua, Truyen Nguyen, Tam Le, Jose Blanchet, Viet Anh Nguyen

• Point-set Distances for Learning Representations of 3D Point Clouds. [Supplementary]
  ICCV, 2021.
  Trung Nguyen, Quang-Hieu Pham, Tam Le, Tung Pham, Nhat Ho, Binh-Son Hua.

• LSMI-Sinkhorn: Semi-supervised Squared-Loss Mutual Information Estimation with Optimal Transport
  ECML-PKDD, 2021.
  Yanbin Liu*, Makoto Yamada*, Yao-Hung Hubert Tsai, Tam Le, Ruslan Salakhutdinov, Yi Yang

• Topological Bayesian Optimization with Persistence Diagrams
  ECAI, 2020.
  Tatsuya Shiraishi, Tam Le, Hisashi Kashima, Makoto Yamada

• On Scalable Variant of Wasserstein Barycenter
  ArXiv, 2019.
  Tam Le*, Viet Huynh*, Nhat Ho*, Dinh Phung, Makoto Yamada

• A General Representation Scheme for Crystalline Solids based on Voronoi-Tessellation Real Feature Values and Atomic Property Data
  STAM Journal, 2018.
  Randy Jalem, Masanobu Nakayama, Yusuke Noda, Tam Le, Ichiro Takeuchi, Yoshitaka Tateyama, Hisatsugu Yamazaki

• Generalized Aitchison Embeddings for Histograms. [SLIDE]
  ACML, 2013. [oral]
  Tam Le, Marco Cuturi

• Image Categorization Using Hierarchical Spatial Matching Kernel
  IIEEJ Journal, 2013.
  Tam Le, Yousun Kang, Akihiro Sugimoto
  (Preliminary conference version in ICIAR, 2011)

• Hierarchical Spatial Matching Kernel for Image Categorization. [SLIDE]
  ICIAR, 2011. [oral]
  Tam Le, Yousun Kang, Akihiro Sugimoto, Son Tran, Thuc Nguyen

• Realtime Traffic Sign Detection Using Color and Shape-Based Features
  ACIIDS, 2010. [oral]
  Tam Le, Son Tran, Seichii Mita, Thuc Nguyen

Thesis

• Geometry-Aware Learning Algorithms for Histogram Data Using Adaptive Metric Embeddings and Kernel Functions
  Ph.D. thesis, Kyoto University, Japan, 2015.