AI Paper Atlas

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

Entropy-based Training Methods for Scalable Neural Implicit Samplers

Weijian Luo, Boya Zhang, Zhihua Zhang

NeurIPS 2023 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Stochastic gradient MCMC · 0 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
Use KL-trained one-step neural sampler instead of LD/HMC with 500 iterationsKL-NS · 2D targetsinference time (s), MOG2: 0.2168 -> 0.0014 (vs LD); 1.7125 -> 0.0014 (vs HMC)Improved
Use KL-NS instead of Fisher-NSNeural sampler · FunnelKSD: 7.837 -> 0.115Improved
Use KL-NS instead of KSD-NSNeural sampler · RosenbrockKSD: 1.531 -> 0.123Improved
Use KL-NS instead of Coupling FlowNeural sampler · RosenbrockKSD: 0.150 -> 0.123Improved
Use SVGD instead of neural samplersSampler · 2D targetsKSD: 0.044 -> 0.104 (MOG2, SVGD vs KL-NS)Improved
Use KL-NS instead of LD with 500 iterationsKL-NS · 2D targetsKSD, MOG2: 0.099 -> 0.104No clear effect
Use Fisher-NS instead of SGLD, DSVI, SVGD and SteinGANFisher-NS · Covertypetest accuracy (%): 75.37% -> 76.22%Improved
Use KL-IS instead of Fisher-NS (ablation)Implicit sampler · Covertypetest accuracy (%): 76.22% -> 75.95%Hurt
Replace annealed Langevin EBM sampling (250 NFE) with one-NFE KL samplerKL Sampler · MNIST EBMFID: 20.95 -> 22.29Mixed
Replace EBM sampling at 100 NFE with one-NFE KL samplerKL Sampler · MNIST EBMFID: 30.35 -> 22.29Improved
Reduce EBM NFE from 250 to 50 (ablation)EBM annealed Langevin · MNIST EBMFID: 20.95 -> 52.55Hurt
Reduce EBM NFE from 150 to 100 (ablation)EBM annealed Langevin · MNIST EBMFID: 21.32 -> 30.35Hurt

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