AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Posterior sampling strategies based on discretized stochastic differential equations for machine learning applications

Frederik Heber, Žofia Trst’anová, Benedict Leimkuhler

JMLR 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Stochastic gradient MCMC · 3 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
add the ensemble quasi-Newton preconditioner with 8 or 16 walkers instead of a single BAOAB walkerBAOAB sampler · Gaussian model samplingintegrated autocorrelation time of slow directions: significantly improves the Integrated Autocorrelation Time for the slow directionsImproved
add the ensemble quasi-Newton preconditioner with 8 or 16 walkersBAOAB sampler · Gaussian model sampling (fast directions)integrated autocorrelation time of fast directionsNo clear effect
use covariance blending eta of 10,000 (EQN) instead of eta=0 (standard Langevin) (ablation)BAOAB sampler with 8 walkers · MNIST two-class (7 vs 9)slowest integrated autocorrelation time: improvement of up to a factor of 4Improved
vary covariance blending constant eta up to very high values (ablation)EQN sampler · MNIST two-class (7 vs 9)integrated autocorrelation timeNo clear effect
increase friction gamma and step size, large potential prefactor a=4 versus a=0.01 (ablation)BAOAB sampler · Harmonic potential kinetic energy errorerror vs step size: slopes -0.44 to 0.08 for a=0.01 versus 0.63 to 1.94 for a=4Mixed
use BAOAB instead of SGLD, GLA1 and GLA2 (ablation)Langevin sampler choice · Two-cluster classification virial erroraccuracy of position marginal: BAOAB reaches the CLT limit while GLA1 slope 0.86, GLA2 2.01Improved
use second-order GLA2 instead of first-order GLA1 (ablation)Geometric Langevin Algorithm · Two-cluster classification virial errorconvergence order: 0.86 -> 2.01Improved
add EQN preconditioning with more walkers (8 to 16) at extra costEQN sampler · MNIST two-class (7 vs 9)per-walker overhead: 40% -> 50%Hurt
use EQN on MNIST with scale-invariant output biases left freeEQN sampler · MNIST two-classIAT reductionNo clear effect

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