AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning

François Denis, Mattias Gybels, Amaury Habrard

JMLR 2016 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use dimension-free Theorem 7 instead of Eq. (3)concentration bound · PAutomaC problem 3bound value: 0.100 -> 0.067Improved
compute sigma^2 over U x V (opt.) rather than Sigma* x Sigma* (ablation)Theorem 7 · PAutomaC problem 15bound value: 0.085 -> 0.028Improved
use Theorem 7 instead of Eq. (3)Hankel bound · PAutomaC problem 15bound value: 0.127 -> 0.085Improved
use Theorem 9 instead of Eq. (3), prefix case eta=1/2prefix Hankel bound · PAutomaC problem 3bound value: 0.140 -> 0.089Improved
compute sigma^2 over U x V for Theorem 9, eta=1/2 (ablation)Theorem 9 · PAutomaC problem 3bound value: 0.089 -> 0.064Improved
use Theorem 9 (opt.) instead of Eq. (3), eta=1prefix Hankel bound · PAutomaC problem 3bound value: 0.281 -> 0.128Improved
use Theorem 11 instead of Eq. (3), factor casefactor Hankel bound · PAutomaC problem 3bound value: 0.148 -> 0.099Improved
compute sigma^2 over U x V for Theorem 11 (ablation)Theorem 11 · PAutomaC problem 3bound value: 0.099 -> 0.060Improved
use factor variant instead of prefix variant of Hankel matrixspectral learning · PAutomaC (11 problems)distance between singular-vector spacesImproved
use prefix variant instead of classical Hankel matrixspectral learning · PAutomaC (11 problems)distance between singular-vector spacesImproved
increase eta from 1/2 to 1 in prefix/factor variantsspectral learning · PAutomaC (11 problems)distance between singular-vector spacesImproved
increase |V| from 100 to 20,000spectral learning · PAutomaC (11 problems)distance between singular-vector spacesHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy