AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

State-by-state Minimax Adaptive Estimation for Nonparametric Hidden {M}arkov Models

Luc Lehéricy

JMLR 2018 · Learning theory and algorithms › Sample complexity · approach: Distributed estimation under communication limits

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 state-by-state selection instead of a single 10-fold cross-validated modelSpectral HMM estimator · Uniform emission densityconvergence rate exponent: -0.434 ± 0.007 -> -0.500 ± 0.046Improved
use state-by-state selection instead of a single 10-fold cross-validated modelSpectral HMM estimator · Symmetrized Beta emission densityconvergence rate exponent: -0.263 ± 0.011 -> -0.347 ± 0.007Improved
use state-by-state selection instead of a single 10-fold cross-validated modelSpectral HMM estimator · Beta emission densityconvergence rate exponent: -0.377 ± 0.008 -> -0.470 ± 0.015Improved
use cross validation instead of state-by-state selection at small nSpectral HMM estimator · Small sample size (n <= 350,000)L2 errorImproved
use state-by-state selection instead of cross validation at large nSpectral HMM estimator · Large sample size (n > 350,000)L2 error: up to one order of magnitudeImproved
add POS variant of final estimator selection to Eachjump (ablation)Eachjump calibration · Symmetrized Beta emission densityconvergence rate exponent: -0.347 ± 0.007 -> -0.327 ± 0.008Hurt
add MAX variant to Jumpmax (ablation)Jumpmax calibration · Symmetrized Beta emission densityconvergence rate exponent: -0.349 ± 0.006 -> -0.404 ± 0.009Improved
replace Eachjump with Jumpmean calibration (ablation)State-by-state selection · Uniform emission densityconvergence rate exponent: -0.500 ± 0.046 -> -0.532 ± 0.048No clear effect
use MAX selection variant instead of standard selection (ablation)State-by-state selection · Small number of observationsL2 errorImproved

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