aiqbench analysis
This research introduces Stream-SW, a novel method for estimating sliced Wasserstein distance directly from data streams with minimal memory overhead. By leveraging quantile approximation techniques on one-dimensional projections, the approach offers theoretical error guarantees and superior accuracy compared to random subsampling in tasks like point cloud classification and change detection. The work advances machine learning methodology by addressing computational scalability constraints inherent in large-scale distribution comparisons.
Streaming Sliced Optimal Transport
arXiv:2505.06835v5 Announce Type: replace Abstract: Sliced optimal transport (SOT), or sliced Wasserstein (SW) distance, is widely recognized for its statistical and computational scalability. In this work, we further enhance computational scalability by proposing the first method for estimating SW from sample streams, called streaming sliced Wasserstein (Stream-SW). To define Stream-SW, we first introduce a streaming estimator of the one-dimensional Wasserstein distance (1DW). Since the 1DW has a closed-form expression, given by the integral of the absolute difference between the quantile functions of the compared distributions, we leverage quantile approximation techniques for sample streams to define a streaming 1DW estimator. By applying the streaming 1DW to all projections, we obtain Stream-SW. The key advantage of Stream-SW is its low memory complexity while providing theoretical guarantees on the approximation error. We demonstrate that Stream-SW achieves a more accurate approximation of SW than random subsampling, with lower memory consumption, when comparing Gaussian distributions and mixtures of Gaussians from streaming samples. Additionally, we conduct experiments on point cloud classification, point cloud gradient flows, and streaming change point detection to further highlight the favorable performance of the proposed Stream-SW.
Abstract:Sliced optimal transport (SOT), or sliced Wasserstein (SW) distance, is widely recognized for its statistical and computational scalability. In this work, we further enhance computational scalability by proposing the first method for estimating SW from sample streams, called streaming sliced Wasserstein (Stream-SW). To define Stream-SW, we first introduce a streaming estimator of the one-dimensional Wasserstein distance (1DW). Since the 1DW has a closed-form expression, given by the integral of the absolute difference between the quantile functions of the compared distributions, we leverage quantile approximation techniques for sample streams to define a streaming 1DW estimator. By applying the streaming 1DW to all projections, we obtain Stream-SW. The key advantage of Stream-SW is its low memory complexity while providing theoretical guarantees on the approximation error. We demonstrate that Stream-SW achieves a more accurate approximation of SW than random subsampling, with lower memory consumption, when comparing Gaussian distributions and mixtures of Gaussians from streaming samples. Additionally, we conduct experiments on point cloud classification, point cloud gradient flows, and streaming change point detection to further highlight the favorable performance of the proposed Stream-SW.
Machine Learning (cs.LG); Computation (stat.CO); Methodology (stat.ME); Machine Learning (stat.ML)
arXiv:2505.06835 [cs.LG]
(or arXiv:2505.06835v5 [cs.LG] for this version)
Full text under the publisher's open licence · 197 words
Related coverage
DI Series: Serving Kimi-K3 MXFP4 Wide-EP Disaggregated on AMD Instinct MI300X and MI325X
AMD · Oct 8, 2026
Scaling AI Inference Across Multiple GPUs Using NVIDIA TensorRT with Multi-Device Inference Support
NVIDIA · Jun 25, 2026
Rivian’s Gambit for Full Autonomy
IEEE Spectrum · Sep 8, 2026
Data-Driven Design Optimization of Streaming-Potential-Mediated Electrokinetic Transport of Viscoelastic Fluids in Microchannels
arXiv · Sep 1, 2026