11 papers · 1 filter
Vertical Sliced Wasserstein Distances for Meta-Measures
Elaheh Akbari, Ahmadreza Moradipari, Kyungtae Han +4
Many modern learning problems require comparing probability distributions whose individual observations are themselves probability measures, naturally giving rise to meta-measures…
SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
Yikun Bai, Binghang Lu, Yikai Liu +7
Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties. Existing diffusion and flow-matching models p…
Generalized Discrete Diffusion with Self-Correction
Linxuan Wang, Ziyi Wang, Yikun Bai +3
Self-correction is an effective technique for maintaining parallel sampling in discrete diffusion models with minimal performance degradation. Prior work has explored self-correcti…
LUNA: Linear Universal Neural Attention with Generalization Guarantees
Ashkan Shahbazi, Ping He, Ali Abbasi +6
Scaling attention faces a critical bottleneck: the quadratic computational cost of softmax attention, which limits its application in long-sequence domains. Whil…
LOTFormer: Doubly-Stochastic Linear Attention via Low-Rank Optimal Transport
Ashkan Shahbazi, Chayne Thrash, Yikun Bai +3
Transformers have proven highly effective across modalities, but standard softmax attention scales quadratically with sequence length, limiting long context modeling. Linear attent…
OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation
Elaheh Akbari, Shansita Sharma, Ping He +5
Flow-matching models have recently emerged as a powerful framework for generative modeling, including 3D point cloud synthesis. However, their deployment is limited by the need for…
Fused Partial Gromov-Wasserstein for Structured Objects
Yikun Bai, Shuang Wang, Huy Tran +3
Structured data, such as graphs, is vital in machine learning due to its capacity to capture complex relationships and interactions. In recent years, the Fused Gromov-Wasserstein (…
Understanding Learning with Sliced-Wasserstein Requires Rethinking Informative Slices
Huy Tran, Yikun Bai, Ashkan Shahbazi +2
The practical applications of Wasserstein distances (WDs) are constrained by their sample and computational complexities. Sliced-Wasserstein distances (SWDs) provide a workaround b…
Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data
Xinran Liu, Yikun Bai, Rocío Díaz Martín +5
Efficient comparison of spherical probability distributions becomes important in fields such as computer vision, geosciences, and medicine. Sliced optimal transport distances, such…
Expected Sliced Transport Plans
Xinran Liu, Rocío Díaz Martín, Yikun Bai +4
The optimal transport (OT) problem has gained significant traction in modern machine learning for its ability to: (1) provide versatile metrics, such as Wasserstein distances and t…
Linear Partial Gromov-Wasserstein Embedding
Yikun Bai, Abihith Kothapalli, Hengrong Du +2
The Gromov-Wasserstein (GW) problem, a variant of the classical optimal transport (OT) problem, has attracted growing interest in the machine learning and data science communities…