REVIEW 8 cited by
Target Score Matching
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Denoising Score Matching estimates the score of a noised version of a target distribution by minimizing a regression loss and is widely used to train the popular class of Denoising Diffusion Models. A well known limitation of Denoising Score Matching, however, is that it yields poor estimates of the score at low noise levels. This issue is particularly unfavourable for problems in the physical sciences and for Monte Carlo sampling tasks for which the score of the clean original target is known. Intuitively, estimating the score of a slightly noised version of the target should be a simple task in such cases. In this paper, we address this shortcoming and show that it is indeed possible to leverage knowledge of the target score. We present a Target Score Identity and corresponding Target Score Matching regression loss which allows us to obtain score estimates admitting favourable properties at low noise levels.
Forward citations
Cited by 8 Pith papers
-
Bayesian Experimental Design via Score Matching
SCOREBED isolates EIG double intractability in a policy-independent score-matching stage, then trains design policies with a singly intractable gradient estimator, enabling cheap multi-policy selection.
-
Inverting Data Transformations via Diffusion Sampling
A Lie-group diffusion sampler that inverts unknown data transformations at test time, using only an energy function, and improves pretrained models on affine/homography images and PDE solving.
-
Diffusion Models for Inverse Problems in the Exponential Family
The evidence trick approximates the likelihood score in diffusion inverse problems for exponential family observations by integrating the likelihood against a conjugate variational posterior, enabling Poisson and Bino...
-
ATLAS: A Foundation Neural Sampler for Amorphous Materials
ATLAS is a force-trained diffusion sampler that generates Boltzmann-distributed amorphous structures, estimates free energies, and drives multi-objective inverse design of metallic glasses.
-
Markov Chain Monte Carlo with Diffusion Paths
MAD-Path uses forward–backward diffusion paths as Metropolis proposals so multimodal targets stay invariant and mode weights are preserved better than under tempering.
-
FES-FM: Free Energy Surface Sampling via Reduced Flow Matching
FES-FM learns a reduced flow-matching transport in collective-variable space to sample free energy surfaces, cutting per-sample generation cost while leaving full-space training cost unchanged.
-
No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers
Simulation-free training of neural samplers fails without Langevin preconditioning, and parallel tempering followed by fitting a diffusion model is a stronger baseline than most neural samplers.
-
Density Ratio Estimation with Conditional Probability Paths
Conditional Time Score Matching estimates density ratios by regressing closed-form conditional time scores, giving faster learning and theoretical error bounds.
Discussion (0). Continue with ORCID to comment.