Scalable and consistent embedding of probability measures into Hilbert spaces via measure quantization
This paper is focused on statistical learning from data that come as probability measures. In this setting, popular approaches consist in embedding such data into a Hilbert space with either Linearized Optimal Transport or Kernel Mean Embedding. However, the cost of computing such embeddings prohibits their direct use in large-scale settings. We study two methods based on measure quantization for approximating input probability measures with discrete measures of small-support size. The first one is based on optimal quantization of each input measure, while the second one relies on mean-measure quantization. We study the consistency of such approximations, and its implication for scalable embeddings of probability measures into a Hilbert space at a low computational cost. We finally illustrate our findings with various numerical experiments.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationSimilar Papers 제목 키워드 기반
Wasserstein Gradient Flows for Scalable and Regularized Barycenter Computation
Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not scalable as they assume access to the co…
Domain AdaptationSobolev Transport: A Scalable Metric for Probability Measures with Graph Metrics
Optimal transport (OT) is a popular measure to compare probability distributions. However, OT suffers a few drawbacks such as (i) a high complexity for computation, (ii) indefiniteness which limits its applicability to k…
Document ClassificationTopological Data AnalysisWord EmbeddingsPCA of probability measures: Sparse and Dense sampling regimes
A common approach to perform PCA on probability measures is to embed them into a Hilbert space where standard functional PCA techniques apply. While convergence rates for estimating the embedding of a single measure from…
A Fast, Consistent Kernel Two-Sample Test
A kernel embedding of probability distributions into reproducing kernel Hilbert spaces (RKHS) has recently been proposed, which allows the comparison of two probability measures P and Q based on the distance between the…
Vocal Bursts Valence PredictionVERSE: Versatile Graph Embeddings from Similarity Measures
Embedding a web-scale information network into a low-dimensional vector space facilitates tasks such as link prediction, classification, and visualization. Past research has addressed the problem of extracting such embed…
Link Prediction