Flow Annealed Importance Sampling Bootstrap

• URL: http://arxiv.org/abs/2208.01893v1
• Date: Wed, 3 Aug 2022 07:44:48 GMT
• Title: Flow Annealed Importance Sampling Bootstrap
• Authors: Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm, Bernhard Sch\"olkopf, Jos\'e Miguel Hern\'andez-Lobato
• Abstract summary: Flow AIS Bootstrap (FAB) is a tractable density model that approximates complex target distributions. We show that FAB produces better results than training via maximum likelihood on MD samples while using 100 times fewer target evaluations. We are the first to learn the Boltzmann distribution of the alanine dipeptide molecule using only the target density.
• Score: 11.458583322083125
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Normalizing flows are tractable density models that can approximate complicated target distributions, e.g. Boltzmann distributions of physical systems. However, current methods for training flows either suffer from mode-seeking behavior, use samples from the target generated beforehand by expensive MCMC simulations, or use stochastic losses that have very high variance. To avoid these problems, we augment flows with annealed importance sampling (AIS) and minimize the mass covering $\alpha$-divergence with $\alpha=2$, which minimizes importance weight variance. Our method, Flow AIS Bootstrap (FAB), uses AIS to generate samples in regions where the flow is a poor approximation of the target, facilitating the discovery of new modes. We target with AIS the minimum variance distribution for the estimation of the $\alpha$-divergence via importance sampling. We also use a prioritized buffer to store and reuse AIS samples. These two features significantly improve FAB's performance. We apply FAB to complex multimodal targets and show that we can approximate them very accurately where previous methods fail. To the best of our knowledge, we are the first to learn the Boltzmann distribution of the alanine dipeptide molecule using only the unnormalized target density and without access to samples generated via Molecular Dynamics (MD) simulations: FAB produces better results than training via maximum likelihood on MD samples while using 100 times fewer target evaluations. After reweighting samples with importance weights, we obtain unbiased histograms of dihedral angles that are almost identical to the ground truth ones.

Related papers

• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [49.97755400231656]
  We present the first performance guarantee with explicit dimensional general score-mismatched diffusion samplers. We show that score mismatches result in an distributional bias between the target and sampling distributions, proportional to the accumulated mismatch between the target and training distributions. This result can be directly applied to zero-shot conditional samplers for any conditional model, irrespective of measurement noise.
  arXiv  Detail & Related papers  (2024-10-17T16:42:12Z)
• Iterated Denoising Energy Matching for Sampling from Boltzmann Densities [109.23137009609519]
  Iterated Denoising Energy Matching (iDEM) iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our matching objective. We show that the proposed approach achieves state-of-the-art performance on all metrics and trains $2-5times$ faster.
  arXiv  Detail & Related papers  (2024-02-09T01:11:23Z)
• Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance [1.6804613362826175]
  Diffusion models have emerged as a pivotal advancement in generative models. In this paper we aim to underscore a discrepancy between conventional training methods and the desired conditional sampling behavior. We introduce an updated loss function that better aligns training objectives with sampling behaviors.
  arXiv  Detail & Related papers  (2023-11-02T02:03:12Z)
• Simulation-free Schr\"odinger bridges via score and flow matching [89.4231207928885]
  We present simulation-free score and flow matching ([SF]$2$M) Our method generalizes both the score-matching loss used in the training of diffusion models and the recently proposed flow matching loss used in the training of continuous flows. Notably, [SF]$2$M is the first method to accurately model cell dynamics in high dimensions and can recover known gene regulatory networks simulated data.
  arXiv  Detail & Related papers  (2023-07-07T15:42:35Z)
• Towards Understanding and Improving GFlowNet Training [71.85707593318297]
  We introduce an efficient evaluation strategy to compare the learned sampling distribution to the target reward distribution. We propose prioritized replay training of high-reward $x$, relative edge flow policy parametrization, and a novel guided trajectory balance objective.
  arXiv  Detail & Related papers  (2023-05-11T22:50:41Z)
• Multisample Flow Matching: Straightening Flows with Minibatch Couplings [38.82598694134521]
  Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples. We propose Multisample Flow Matching, a more general framework that uses non-trivial couplings between data and noise samples. We show that our proposed methods improve sample consistency on downsampled ImageNet data sets, and lead to better low-cost sample generation.
  arXiv  Detail & Related papers  (2023-04-28T11:33:08Z)
• Bias Mimicking: A Simple Sampling Approach for Bias Mitigation [57.17709477668213]
  We introduce a new class-conditioned sampling method: Bias Mimicking. Bias Mimicking improves underrepresented groups' accuracy of sampling methods by 3% over four benchmarks.
  arXiv  Detail & Related papers  (2022-09-30T17:33:00Z)
• Bootstrap Your Flow [4.374837991804085]
  We develop a new flow-based training procedure, FAB (Flow AIS Bootstrap), to produce accurate approximations to complex target distributions. We demonstrate that FAB can be used to produce accurate approximations to complex target distributions, including Boltzmann distributions, in problems where previous flow-based methods fail.
  arXiv  Detail & Related papers  (2021-11-22T20:11:47Z)
• Unrolling Particles: Unsupervised Learning of Sampling Distributions [102.72972137287728]
  Particle filtering is used to compute good nonlinear estimates of complex systems. We show in simulations that the resulting particle filter yields good estimates in a wide range of scenarios.
  arXiv  Detail & Related papers  (2021-10-06T16:58:34Z)
• Improved Denoising Diffusion Probabilistic Models [4.919647298882951]
  We show that DDPMs can achieve competitive log-likelihoods while maintaining high sample quality. We also find that learning variances of the reverse diffusion process allows sampling with an order of magnitude fewer forward passes. We show that the sample quality and likelihood of these models scale smoothly with model capacity and training compute, making them easily scalable.
  arXiv  Detail & Related papers  (2021-02-18T23:44:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.