SOTAVerified

Density Estimation

The goal of Density Estimation is to give an accurate description of the underlying probabilistic density distribution of an observable data set with unknown density.

Source: Contrastive Predictive Coding Based Feature for Automatic Speaker Verification

Papers

Showing 326–350 of 1394 papers

TitleStatusHype
Bounded rationality in structured density estimation—0
Bounded rationality in structured density estimation—0
Latent Space Energy-based Model for Fine-grained Open Set Recognition—0
Crowdotic: A Privacy-Preserving Hospital Waiting Room Crowd Density Estimation with Non-speech Audio—0
Content Reduction, Surprisal and Information Density Estimation for Long Documents—0
Correcting sampling biases via importance reweighting for spatial modeling—0
NeuroCodeBench: a plain C neural network benchmark for software verificationCode0
Tropical Geometric Tools for Machine Learning: the TML packageCode0
Distribution learning via neural differential equations: a nonparametric statistical perspective—0
Affine-Transformation-Invariant Image Classification by Differentiable Arithmetic Distribution Module—0
Self-Supervision for Tackling Unsupervised Anomaly Detection: Pitfalls and Opportunities—0
Arbitrary Distributions Mapping via SyMOT-Flow: A Flow-based Approach Integrating Maximum Mean Discrepancy and Optimal Transport—0
Out-of-distribution detection using normalizing flows on the data manifold—0
Bayesian Exploration Networks—0
Towards Automated Animal Density Estimation with Acoustic Spatial Capture-Recapture—0
Conditional Kernel Imitation Learning for Continuous State Environments—0
Cell Spatial Analysis in Crohn's Disease: Unveiling Local Cell Arrangement Pattern with Graph-based SignaturesCode0
Fast Inference and Update of Probabilistic Density Estimation on Trajectory PredictionCode1
High-Probability Risk Bounds via Sequential Predictors—0
Learning Distributions via Monte-Carlo Marginalization—0
Generative Forests—0
Statistical Estimation Under Distribution Shift: Wasserstein Perturbations and Minimax TheoryCode0
Adaptive learning of density ratios in RKHS—0
Continual Learning in Predictive Autoscaling—0
MVMR-FS : Non-parametric feature selection algorithm based on Maximum inter-class Variation and Minimum Redundancy—0
Show:102550
← PrevPage 14 of 56Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MAFLog-likelihood (nats)3,049—Unverified
2DDPMNLL (bits/dim)3.69—Unverified
3MRCNFNLL (bits/dim)3.54—Unverified
4FFJORDNLL (bits/dim)3.4—Unverified
5RNODENLL (bits/dim)3.38—Unverified
6Pixel CNNNLL (bits/dim)3.03—Unverified
7score SDENLL (bits/dim)2.99—Unverified
8Flow matchingNLL (bits/dim)2.99—Unverified
9Pixel CNN ++NLL (bits/dim)2.92—Unverified
10Image TransformerNLL (bits/dim)2.9—Unverified
#ModelMetricClaimedVerifiedStatus
1DVP-VAENLL77.1—Unverified
2PaddingFlowMMD-L211—Unverified
3FFJORDNLL (bits/dim)0.99—Unverified
4RNODENLL (bits/dim)0.97—Unverified
5IdentityNLL (bits/dim)0.13—Unverified
6MADE MoGLog-likelihood (nats)-1,038.5—Unverified
#ModelMetricClaimedVerifiedStatus
1nMDMALog-likelihood1.78—Unverified
2DDELog-likelihood0.97—Unverified
3B-NAFLog-likelihood0.61—Unverified
4FFJORDLog-likelihood0.46—Unverified
5MADE MoGLog-likelihood0.4—Unverified
6PaddingFlowCD0.14—Unverified
#ModelMetricClaimedVerifiedStatus
1TANLog-likelihood159.8—Unverified
2FFJORDLog-likelihood157.4—Unverified
3B-NAFLog-likelihood157.36—Unverified
4MADE MoGLog-likelihood153.71—Unverified
5PaddingFlowCD0.5—Unverified
#ModelMetricClaimedVerifiedStatus
1GlowNLL (bits/dim)4.09—Unverified
2Image TransformerNLL (bits/dim)3.77—Unverified
3VDMNLL (bits/dim)3.72—Unverified
4i-DODENLL (bits/dim)3.69—Unverified
5MuLANNLL (bits/dim)3.67—Unverified
#ModelMetricClaimedVerifiedStatus
1B-NAFLog-likelihood12.06—Unverified
2DDELog-likelihood9.73—Unverified
3FFJORDLog-likelihood8.59—Unverified
4MADE MoGLog-likelihood8.47—Unverified
5PaddingFlowCD0.89—Unverified
#ModelMetricClaimedVerifiedStatus
1PaddingFlowCD13.8—Unverified
2DDELog-likelihood-11.3—Unverified
3B-NAFLog-likelihood-14.71—Unverified
4FFJORDLog-likelihood-14.92—Unverified
5MADE MoGLog-likelihood-15.15—Unverified
#ModelMetricClaimedVerifiedStatus
1PaddingFlowCD24.5—Unverified
2DDELog-likelihood-6.94—Unverified
3B-NAFLog-likelihood-8.95—Unverified
4FFJORDLog-likelihood-10.43—Unverified
5MADE MoGLog-likelihood-12.27—Unverified
#ModelMetricClaimedVerifiedStatus
1FFJORDNegative ELBO98.33—Unverified
2B-NAFNegative ELBO94.83—Unverified
3DVp-VAENLL89.07—Unverified
4PaddingFlowMMD-L220.3—Unverified
#ModelMetricClaimedVerifiedStatus
1FFJORDNegative ELBO104.03—Unverified
2B-NAFNegative ELBO94.91—Unverified
3PaddingFlowMMD-L217.9—Unverified
#ModelMetricClaimedVerifiedStatus
1FFJORDNegative ELBO4.39—Unverified
2B-NAFNegative ELBO4.33—Unverified
3PaddingFlowMMD-L20.62—Unverified
#ModelMetricClaimedVerifiedStatus
1RNODELog-likelihood1.04—Unverified
#ModelMetricClaimedVerifiedStatus
1MAFLog-likelihood5,872—Unverified
#ModelMetricClaimedVerifiedStatus
1RNODELog-likelihood3.83—Unverified