2025
Many-to-Many Matching via Sparsity Controlled Optimal Transport.
CoRR, March, 2025
Any-stepsize Gradient Descent for Separable Data under Fenchel-Young Losses.
CoRR, February, 2025
Scalable individual treatment effect estimator for large graphs.
Mach. Learn., January, 2025
Online Inverse Linear Optimization: Improved Regret Bound, Robustness to Suboptimality, and Toward Tight Regret Analysis.
CoRR, January, 2025
Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel-Young Loss Perspective and Gap-Dependent Regret Analysis.
CoRR, January, 2025
Necessary and Sufficient Watermark for Large Language Models.
Trans. Mach. Learn. Res., 2025
PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025
2024
Polyak Meets Parameter-free Clipped Gradient Descent.
CoRR, 2024
Online Policy Learning from Offline Preferences.
CoRR, 2024
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Parameter-free Clipped Gradient Descent Meets Polyak.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Self-attention Networks Localize When QK-eigenspectrum Concentrates.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Online Structured Prediction with Fenchel-Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss.
Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024
Fast 1-Wasserstein distance approximations using greedy strategies.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024
2023
Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data.
Trans. Mach. Learn. Res., 2023
Embarrassingly Simple Text Watermarks.
CoRR, 2023
Feature Normalization Prevents Collapse of Non-contrastive Learning Dynamics.
CoRR, 2023
Estimating Treatment Effects Under Heterogeneous Interference.
Proceedings of the Machine Learning and Knowledge Discovery in Databases: Research Track, 2023
Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Will Large-scale Generative Models Corrupt Future Datasets?
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Proper Losses, Moduli of Convexity, and Surrogate Regret Bounds.
Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023
Unbalanced Optimal Transport for Unbalanced Word Alignment.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023
2022
Approximating 1-Wasserstein Distance with Trees.
Trans. Mach. Learn. Res., 2022
Sparse Regularized Optimal Transport with Deformed q-Entropy.
Entropy, 2022
On the Surrogate Gap between Contrastive and Supervised Losses.
Proceedings of the International Conference on Machine Learning, 2022
Pairwise Supervision Can Provably Elicit a Decision Boundary.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022
Robust computation of optimal transport by β-potential regularization.
Proceedings of the Asian Conference on Machine Learning, 2022
2021
Classification From Pairwise Similarities/Dissimilarities and Unlabeled Data via Empirical Risk Minimization.
Neural Comput., 2021
Sharp Learning Bounds for Contrastive Unsupervised Representation Learning.
CoRR, 2021
Learning from Noisy Similar and Dissimilar Data.
Proceedings of the Machine Learning and Knowledge Discovery in Databases. Research Track, 2021
Fenchel-Young Losses with Skewed Entropies for Class-posterior Probability Estimation.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021
2020
Similarity-based Classification: Connecting Similarity Learning to Binary Classification.
CoRR, 2020
Calibrated Surrogate Maximization of Dice.
Proceedings of the Medical Image Computing and Computer Assisted Intervention - MICCAI 2020, 2020
Calibrated Surrogate Losses for Adversarially Robust Classification.
Proceedings of the Conference on Learning Theory, 2020
Calibrated Surrogate Maximization of Linear-fractional Utility in Binary Classification.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020
2019
Imitation Learning from Imperfect Demonstration.
Proceedings of the 36th International Conference on Machine Learning, 2019
Unsupervised Domain Adaptation Based on Source-Guided Discrepancy.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019
2018
Convex formulation of multiple instance learning from positive and unlabeled bags.
Neural Networks, 2018
Classification from Pairwise Similarity and Unlabeled Data.
Proceedings of the 35th International Conference on Machine Learning, 2018
2017
Risk Minimization Framework for Multiple Instance Learning from Positive and Unlabeled Bags.
CoRR, 2017