AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Mixing times of data-augmentation Gibbs samplers for high-dimensional probit regression

Filippo Ascolani, Giacomo Zanella

JMLR 2026 · Learning theory and algorithms › Sample complexity · approach: Minimax estimation rates · 4 citations (OpenAlex)

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
increase g prior scale from g=1 to g=10DA Gibbs sampler · Imbalanced y=1, n/p=0.2, p=200upper bound on TV mixing time: 11 -> 65Hurt
increase isotropic prior variance from c=1 to c=10DA Gibbs sampler · Well-specified, n/p=3, p=200upper bound on TV mixing time: 11 -> 90Hurt
increase isotropic prior variance from c=1 to c=10Collapsed Gibbs sampler · Well-specified, n/p=3, p=200upper bound on TV mixing time: 31 -> 118Hurt
add an unscaled intercept column with imbalanced dataDA Gibbs sampler · Imbalanced y=1, n/p=3, p=200upper bound on TV mixing time: 9 -> 591Hurt
add an unscaled intercept column with well-specified dataDA Gibbs sampler · Well-specified, n/p=3, p=200upper bound on TV mixing time: 11 -> 17No clear effect
use collapsed instead of DA Gibbs sampler under g prior g=1Collapsed Gibbs sampler · Imbalanced y=1, n/p=3, p=200upper bound on TV mixing time: 6 -> 27Hurt
use collapsed instead of DA Gibbs sampler with c=10 priorCollapsed Gibbs sampler · Well-specified, n/p=0.2, p=200upper bound on TV mixing time: 47 -> 21Improved
replace the DA sampler by the modified DA sampler that treats the intercept separately (ablation)DA Gibbs sampler · Imbalanced data with interceptupper bound on TV mixing timeImproved
scale prior variance as c=b/(1+r) with r=n/pDA Gibbs sampler · Random design, theoryupper bound on TV mixing timeImproved

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