Tam LE - Publications

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

Selected Journals / Conference Papers

• 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⊛.

• 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⊛.

• 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=3.1%]
  Tam Le*, Truyen Nguyen*
  (This paper was selected for 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

• Tree-Sliced Entropy Partial Transport
  Under review.
  Viet-Hoang Tran, Thanh Tran, Thanh T. Chu, Tam Le⊛, Tan M. Nguyen⊛.

• Revisiting Tree-Sliced Wasserstein Distance Through the Lens of the Fermat–Weber Problem
  Under review.
  Viet-Hoang Tran, Thanh T. Chu, Thanh Tran, Khang Tran, Tam Le⊛, Tan M. Nguyen⊛.

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

• Orlicz-Sobolev Transport for Unbalanced Measures on a Graph
  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

• Tree-Wasserstein Barycenter for Large-Scale Multilevel Clustering and Scalable Bayes
  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.

Invited Talks

• 2025, Workshop on Optimization and Machine Learning for Data Science and Future Computing, Tokyo, Japan.

• 2025, Statistical Mathematics Seminar Series, Virtual.

• 2025, Foundations and Frontiers: Interdisciplinary Perspectives on Mathematical Optimization workshop, RIKEN AIP, Japan.

• 2024, Statistical Mathematics Seminar Series, Virtual. [SLIDE]

• 2024, Data Science Seminar (Data Descriptive Science), Kyoto, Japan (hybrid).

• 2024, The Mathematics of Data program – Workshop on Optimal Transport and PDEs, IMS, NUS, Singapore. [SLIDE]

• 2023, Data Science Seminar (Data Descriptive Science), Tokyo, Japan. [SLIDE]

• 2023, Statistical Mathematics Seminar Series, Virtual. [SLIDE]

• 2023, CREST Seminar: Innovation of Deep Structured Models with Representation of Mathematical Intelligence, Virtual. [SLIDE]

• 2022, Statistical Mathematics Seminar Series, Virtual. [SLIDE]

• 2022, Optimal Transport Seminar (Data Descriptive Science), Virtual.

• 2022, Kyoto Machine Learning workshop, Kyoto University, Japan (hybrid).

• 2022, Asia Pacific Seminar on Applied Topology and Geometry (APATG), Virtual. [SLIDE]

• 2022, AAAI workshop - OT-SDM: International Workshop on Optimal Transport and Structured Data Modeling, Virtual. [SLIDE]

• 2021, VinAI workshop, Virtual. [SLIDE]

• 2021, RIKEN AIP Open Seminar Series, Virtual. [SLIDE]

• 2019, Institute for Advanced Study, Kyoto University, Japan. [SLIDE]

• 2016, MI2I Open Seminar Series, National Institute for Materials Science, Tsukuba, Japan. [SLIDE]

• 2015, Nagoya Institute of Technology, Japan.

• 2015, Bioinformatics Center, Institute for Chemical Research, Kyoto University, Japan.

• 2015, IST Seminar, Graduate School of Informatics, Kyoto University, Japan. [SLIDE]

• 2014, Lear, INRIA Rhone Alpes, Grenoble, France. [SLIDE]