Pith. sign in

REVIEW 3 cited by

Implicit Diffusion: Efficient Optimization through Stochastic Sampling

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

arxiv 2402.05468 v3 pith:WXLFLQ6P submitted 2024-02-08 cs.LG

classification cs.LG
keywords optimizationsamplingdiffusionsdistributionsimplicitprocessesstochasticadvances
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling processes by optimizing over their parameters. We introduce a general framework for first-order optimization of these processes, that performs jointly, in a single loop, optimization and sampling steps. This approach is inspired by recent advances in bilevel optimization and automatic implicit differentiation, leveraging the point of view of sampling as optimization over the space of probability distributions. We provide theoretical guarantees on the performance of our method, as well as experimental results demonstrating its effectiveness. We apply it to training energy-based models and finetuning denoising diffusions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Bayesian Experimental Design via Score Matching

    stat.ML 2026-07 conditional novelty 7.0 of 10

    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.

  2. A First-order Generative Bilevel Optimization Framework for Diffusion Models

    cs.LG 2025-02 reject novelty 6.0 of 10

    A bilevel first-order method tunes entropy-regularization strength and noise schedules in diffusion models without backpropagating through sampling, improving FID and CLIP over hyperparameter search baselines.

  3. Direct Distributional Optimization for Provable Alignment of Diffusion Models

    cs.LG 2025-02 conditional novelty 6.0 of 10

    A distribution-level optimization framework, dual averaging plus Doob's h-transform, aligns diffusion models with provable convergence and isoperimetry-free sampling.

Pith tools