AI Paper Atlas

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

Optimal Preconditioning and Fisher Adaptive Langevin Sampling

Michalis Titsias

NeurIPS 2023 · Learning theory and algorithms › Matrix and tensor methods · approach: Low-rank approximation theory · 2 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
learn a global preconditioner from score increments using the inverse empirical Fisher matrixMALA · CaravanMedian ESS: 7.144 ± 0.663 -> 1920.903 ± 55.821Improved
learn a global preconditioner from score increments using the inverse empirical Fisher matrixMALA · MNISTMedian ESS: 8.188 ± 0.399 -> 811.522 ± 19.165Improved
learn a global preconditioner from score increments using the inverse empirical Fisher matrixMALA · Inhomogeneous GaussianMedian ESS: 9.793 ± 0.655 -> 2002.579 ± 30.001Improved
learn a global preconditioner from score increments using the inverse empirical Fisher matrixMALA · GP targetMedian ESS: 2007.640 ± 104.867 -> 1923.753 ± 95.820Mixed
use score-function differences without Rao-Blackwellization (ablation)FisherMALA · GP targetMedian ESS: 1923.753 ± 95.820 -> 1916.990 ± 85.208No clear effect
use paired mean and covariance stochastic estimation instead of score increments (ablation)FisherMALA · GP targetMedian ESS: 1923.753 ± 95.820 -> 1583.570 ± 109.241Hurt
use paired mean and covariance stochastic estimation instead of score increments (ablation)FisherMALA · MNISTMedian ESS: 811.522 ± 19.165 -> 13.819 ± 1.127Hurt
adapt directly from score vectors rather than centered score increments (ablation)FisherMALA · CaravanMedian ESS: 1920.903 ± 55.821 -> 14.226 ± 4.429Hurt
adapt directly from score vectors rather than centered score increments (ablation)FisherMALA · GP targetMedian ESS: 1923.753 ± 95.820 -> 518.924 ± 579.639Hurt

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