Optimal Transportation by Orthogonal Coupling Dynamics
Many numerical algorithms and learning tasks rest on solution of the Monge-Kantorovich problem and corresponding Wasserstein distances. While the natural approach is to treat the problem as an infinite-dimensional linear programming, such a methodology severely limits the computational performance due to the polynomial scaling with respect to the sample size along with intensive memory requirements. We propose a novel alternative framework to address the Monge-Kantorovich problem based on a projection type gradient descent scheme. The micro-dynamics is built on the notion of the conditional expectation, where the connection with the opinion dynamics is explored and leveraged to build compact numerical schemes. We demonstrate that the devised dynamics recovers random maps with favourable computational performance. Along with the theoretical insight, the provided dynamics paves the way for innovative approaches to construct numerical schemes for computing optimal transport maps as well as Wasserstein distances.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Orthogonal Gromov-Wasserstein Discrepancy with Efficient Lower Bound
Comparing structured data from possibly different metric-measure spaces is a fundamental task in machine learning, with applications in, e.g., graph classification. The Gromov-Wasserstein (GW) discrepancy formulates a co…
Graph ClassificationDecoupled Orthogonal Dynamics: Regularization for Deep Network Optimizers
Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In deep learning, gradients tend to increa…
Expected Sliced Transport Plans
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 their variants, and (2) determine optimal…
Computational EfficiencyElectric Vehicle Charging Infrastructure Planning: A Scalable Computational Framework
The optimal charging infrastructure planning problem over a large geospatial area is challenging due to the increasing network sizes of the transportation system and the electric grid. The coupling between the electric v…
Profile GenerationOptimal Operation of a Hydrogen-based Building Multi-Energy System Based on Deep Reinforcement Learning
Since hydrogen has many advantages (e.g., free pollution, extensive sources, convenient storage and transportation), hydrogen-based multi-energy systems (HMESs) have received wide attention. However, existing works on th…
Deep Reinforcement Learningenergy managementManagementParameter Prediction