Pith. sign in

REVIEW 5 cited by

Training Neural Samplers with Reverse Diffusive KL Divergence

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2410.12456 v2 pith:5RG5WHVY submitted 2024-10-16 cs.LG stat.ML

Jiajun He , Wenlin Chen , Mingtian Zhang , David Barber , José Miguel Hernández-Lobato This is my paper · ORCID
classification cs.LGstat.ML
keywords reversedivergencetargettrainingdensitiesdiffusivedistributionsmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Training generative models to sample from unnormalized density functions is an important and challenging task in machine learning. Traditional training methods often rely on the reverse Kullback-Leibler (KL) divergence due to its tractability. However, the mode-seeking behavior of reverse KL hinders effective approximation of multi-modal target distributions. To address this, we propose to minimize the reverse KL along diffusion trajectories of both model and target densities. We refer to this objective as the reverse diffusive KL divergence, which allows the model to capture multiple modes. Leveraging this objective, we train neural samplers that can efficiently generate samples from the target distribution in one step. We demonstrate that our method enhances sampling performance across various Boltzmann distributions, including both synthetic multi-modal densities and n-body particle systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Guiding Time-Varying Generative Models with Natural Gradients on Exponential Family Manifold

    stat.ML 2025-02 conditional novelty 6.0 of 10

    Time-varying generative models are guided by natural gradient descent through a time-score projection onto an exponential-family manifold, yielding kernel-based particle update algorithms KiNG and ntKiNG.

  2. No Trick, No Treat: Pursuits and Challenges Towards Simulation-free Training of Neural Samplers

    cs.LG 2025-02 conditional novelty 6.0 of 10

    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.

  3. Towards Adaptive External Communication in Autonomous Vehicles: A Conceptual Design Framework

    cs.HC 2025-08 unverdicted novelty 5.0 of 10

    A three-layer framework (input, processing, output) for adaptive external human-machine interfaces in autonomous vehicles is introduced to systematize design and analysis.

  4. Importance Weighted Score Matching for Diffusion Samplers with Enhanced Mode Coverage

    cs.LG 2025-05 conditional novelty 5.0 of 10

    Importance Weighted Score Matching trains diffusion samplers by reweighting score matching with self-normalized importance sampling to approximate the forward KL and improve mode coverage.

  5. Neural Flow Samplers with Shortcut Models

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Neural Flow Shortcut Sampler (NFS2) estimates the partition-function derivative with velocity-driven SMC and Stein control variates, and adds a generalized shortcut consistency loss for few-step sampling.

Pith tools