AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Adaptive Geometric Multiscale Approximations for Intrinsically Low-dimensional Data

Wenjing Liao, Mauro Maggioni

JMLR 2019 · Learning theory and algorithms › Sample complexity · approach: Learning under log-concave distributions

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 adaptive GMRA instead of uniform-scale GMRAGMRA · 4-dim Z manifold, noise-free, L2 error vs nrate of convergence: Adaptive GMRA yields a faster rate of convergence than GMRAImproved
use GMRA instead of nearest neighbor approximationNearest Neighbor · 4-dim S and Z manifolds, noise-freeL2 error and convergence rate: NN rate 1/d = 0.25; GMRA smaller error and faster rateImproved
use larger kappa threshold (0.5 or 1) in adaptive GMRA under noise sigma = 0.05 (ablation)Adaptive GMRA · 4-dim manifolds, sigma = 0.05rate of convergence: kappa = 0.5 and 1 give the fastest rate; kappa = 0.05 is similar to nearest neighborImproved
vary kappa among sufficiently large values in adaptive GMRA (ablation)Adaptive GMRA · 4-dim manifolds, sigma = 0.05rate of convergence: different errors up to a constant, same rateNo clear effect
increase training noise level sigma (ablation)GMRA and adaptive GMRA · 4-dim S and Z manifolds, n = 1e5average L2 approximation error: error increases linearly with sigmaHurt
increase sample size n beyond the noise levelGMRA · 4-dim manifolds, sigma = 0.05L2 error vs noise level: approximation error falls below sigma as n increasesImproved

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