Bootstrap Your Flow

• URL: http://arxiv.org/abs/2111.11510v1
• Date: Mon, 22 Nov 2021 20:11:47 GMT
• Title: Bootstrap Your Flow
• Authors: Laurence Illing Midgley, Vincent Stimper, Gregor N. C. Simm, Jos\'e Miguel Hern\'andez-Lobato
• Abstract summary: 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.
• Score: 4.374837991804085
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Normalising flows are flexible, parameterized distributions that can be used to approximate expectations from intractable distributions via importance sampling. However, current flow-based approaches are limited on challenging targets where they either suffer from mode seeking behaviour or high variance in the training loss, or rely on samples from the target distribution, which may not be available. To address these challenges, we combine flows with annealed importance sampling (AIS), while using the $\alpha$-divergence as our objective, in a novel training procedure, FAB (Flow AIS Bootstrap). Thereby, the flow and AIS to improve each other in a bootstrapping manner. 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.

Related papers

• Learned Reference-based Diffusion Sampling for multi-modal distributions [2.1383136715042417]
  We introduce Learned Reference-based Diffusion Sampler (LRDS), a methodology specifically designed to leverage prior knowledge on the location of the target modes. LRDS proceeds in two steps by learning a reference diffusion model on samples located in high-density space regions. We experimentally demonstrate that LRDS best exploits prior knowledge on the target distribution compared to competing algorithms on a variety of challenging distributions.
  arXiv  Detail & Related papers  (2024-10-25T10:23:34Z)
• 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)
• Improved off-policy training of diffusion samplers [93.66433483772055]
  We study the problem of training diffusion models to sample from a distribution with an unnormalized density or energy function. We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods. Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work.
  arXiv  Detail & Related papers  (2024-02-07T18:51:49Z)
• Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization [87.21285093582446]
  Diffusion Generative Flow Samplers (DGFS) is a sampling-based framework where the learning process can be tractably broken down into short partial trajectory segments. Our method takes inspiration from the theory developed for generative flow networks (GFlowNets)
  arXiv  Detail & Related papers  (2023-10-04T09:39:05Z)
• Efficient Multimodal Sampling via Tempered Distribution Flow [11.36635610546803]
  We develop a new type of transport-based sampling method called TemperFlow. Various experiments demonstrate the superior performance of this novel sampler compared to traditional methods. We show its applications in modern deep learning tasks such as image generation.
  arXiv  Detail & Related papers  (2023-04-08T06:40:06Z)
• Distributional GFlowNets with Quantile Flows [73.73721901056662]
  Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a policy for generating complex structure through a series of decision-making steps. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. Our proposed textitquantile matching GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty.
  arXiv  Detail & Related papers  (2023-02-11T22:06:17Z)
• Flow Matching for Generative Modeling [44.66897082688762]
  Flow Matching is a simulation-free approach for training Continuous Normalizing Flows (CNFs) We find that employing FM with diffusion paths results in a more robust and stable alternative for training diffusion models. Training CNFs using Flow Matching on ImageNet leads to state-of-the-art performance in terms of both likelihood and sample quality.
  arXiv  Detail & Related papers  (2022-10-06T08:32:20Z)
• Flow Annealed Importance Sampling Bootstrap [11.458583322083125]
  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.
  arXiv  Detail & Related papers  (2022-08-03T07:44:48Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Distributional Reinforcement Learning via Moment Matching [54.16108052278444]
  We formulate a method that learns a finite set of statistics from each return distribution via neural networks. Our method can be interpreted as implicitly matching all orders of moments between a return distribution and its Bellman target. Experiments on the suite of Atari games show that our method outperforms the standard distributional RL baselines.
  arXiv  Detail & Related papers  (2020-07-24T05:18:17Z)

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.