AI Paper Atlas

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

``Noisier'’ Noise Contrastive Estimation is (Almost) Maximum Likelihood

Peiyu Yu, Dinghuai Zhang, Hengzhi He, Xiaojian Ma, Sirui Xie, RUIYAO MIAO, Yifan Lu, Yasi Zhang, Deqian Kong, Ruiqi Gao, Jianwen Xie, Guang Cheng and 1 more

ICLR 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis

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
scale noise magnitude M from 1 to 100 (ablation)LEBM on CelebAHQ (nz=512) · CelebAHQ FIDFID: 118.84 -> 101.71Improved
add multi-stage ratio estimation (K=3 vs K=1) (ablation)N2CE-LEBM · CelebAHQ FIDFID: 101.71 -> 95.66Improved
N2CE instead of MLE with short-run Langevin (ablation)LEBM · SVHN FIDFID: 32.74 -> 25.63Improved
N2CE (M=100) instead of NCE (ablation)DxMI reward learning · CIFAR-10 FIDFID: 3.93 -> 2.99Improved
N2CE (M=100) instead of NCE (ablation)DxMI reward learning · ImageNet64x64 FIDFID: 2.69 -> 2.23Improved
N2CE (M=50) instead of NCE (M=1) critic (ablation)SiD · CIFAR-10 unconditional FIDFID: 1.53 -> 1.45Improved
N2CE (M=50) instead of NCE (M=1) critic (ablation)SiD · ImageNet64x64 FIDFID: 1.28 -> 1.11Improved
N2CE instead of NCE in DAMC prior (ablation)DAMC anomaly detection · MNIST held-out digit 9 AUPRCAUPRC: 0.502 -> 0.854Improved
N2CE instead of NCE in DAMC prior (ablation)DAMC anomaly detection · MNIST held-out digit 7 AUPRCAUPRC: 0.605 -> 0.845Mixed
N2CE (M=100,K=6) instead of MLE-LEBM with LD sampler (ablation)offline BBO · Design-Bench mean scoremean score: 0.562 -> 0.748Improved
N2CE (M=100,K=6) instead of NCE (M=1,K=6) with SVGD (ablation)offline BBO · Design-Bench mean scoremean score: 0.770 -> 0.827Improved
reduce stages from K=6 to K=1 in N2CE (ablation)offline BBO · Design-Bench mean scoremean score: 0.827 -> 0.764Hurt

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