LGMLSep 14, 2020

When compressive learning fails: blame the decoder or the sketch?

arXiv:2009.08273v11 citations
Originality Synthesis-oriented
AI Analysis

This addresses a theoretical problem for researchers in compressive learning, but appears incremental as it focuses on analyzing existing methods.

The paper investigates why compressive learning fails by analyzing the non-convex optimization landscape and heuristics like CLOMPR through numerical simulations, but does not report specific results or numbers.

In compressive learning, a mixture model (a set of centroids or a Gaussian mixture) is learned from a sketch vector, that serves as a highly compressed representation of the dataset. This requires solving a non-convex optimization problem, hence in practice approximate heuristics (such as CLOMPR) are used. In this work we explore, by numerical simulations, properties of this non-convex optimization landscape and those heuristics.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes