Compressive statistical learning with random feature moments (Q2664824): Difference between revisions
From MaRDI portal
Created a new Item |
Added link to MaRDI item. |
||
links / mardi / name | links / mardi / name | ||
Revision as of 11:48, 3 February 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Compressive statistical learning with random feature moments |
scientific article |
Statements
Compressive statistical learning with random feature moments (English)
0 references
18 November 2021
0 references
Summary: We describe a general framework -- \textit{compressive statistical learning} -- for resource-efficient large-scale learning: the training collection is compressed in one pass into a low-dimensional \textit{sketch} (a vector of random empirical generalized moments) that captures the information relevant to the considered learning task. A near-minimizer of the risk is computed from the sketch through the solution of a nonlinear least squares problem. We investigate sufficient sketch sizes to control the generalization error of this procedure. The framework is illustrated on compressive PCA, compressive clustering, and compressive Gaussian mixture Modeling with fixed known variance. The latter two are further developed in a companion paper [Math. Stat. Learn. 3, No. 2, 165--257 (2020; Zbl 1478.62165)].
0 references
kernel mean embedding
0 references
random features
0 references
random moments
0 references
statistical learning
0 references
dimension reduction
0 references