Mitigating mode collapse in normalizing flows by annealing with an adaptive schedule: Application to parameter estimation

• URL: http://arxiv.org/abs/2505.03652v1
• Date: Tue, 06 May 2025 15:58:48 GMT
• Title: Mitigating mode collapse in normalizing flows by annealing with an adaptive schedule: Application to parameter estimation
• Authors: Yihang Wang, Chris Chi, Aaron R. Dinner,
• Abstract summary: We show that an adaptive schedule based on the effective sample size (ESS) can mitigate mode collapse.<n>We demonstrate that our approach can converge the marginal likelihood for a biochemical oscillator model fit to time-series data in ten-fold less time than a widely used ensemble Markov chain Monte Carlo method.
• Score: 0.6258471240250307
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Normalizing flows (NFs) provide uncorrelated samples from complex distributions, making them an appealing tool for parameter estimation. However, the practical utility of NFs remains limited by their tendency to collapse to a single mode of a multimodal distribution. In this study, we show that annealing with an adaptive schedule based on the effective sample size (ESS) can mitigate mode collapse. We demonstrate that our approach can converge the marginal likelihood for a biochemical oscillator model fit to time-series data in ten-fold less computation time than a widely used ensemble Markov chain Monte Carlo (MCMC) method. We show that the ESS can also be used to reduce variance by pruning the samples. We expect these developments to be of general use for sampling with NFs and discuss potential opportunities for further improvements.

Related papers

• Accelerated Parallel Tempering via Neural Transports [31.81728174953862]
  Parallel Tempering (PT) enhances MCMC's sample efficiency through parallel computation.<n>We introduce a framework that accelerates PT by leveraging neural samplers.<n>We demonstrate theoretically and empirically on a variety of multimodal sampling problems that our method improves sample quality.
  arXiv  Detail & Related papers  (2025-02-14T17:41:44Z)
• AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning [1.644043499620662]
  Explicit generators, such as Normalising Flows (NFs), have been extensively applied to get unbiased samples from target distributions. We study central problems in conditional NFs, such as high variance, mode collapse and data efficiency. We propose adversarial training for NFs to ameliorate these problems.
  arXiv  Detail & Related papers  (2024-01-29T08:13:51Z)
• Online Variational Sequential Monte Carlo [49.97673761305336]
  We build upon the variational sequential Monte Carlo (VSMC) method, which provides computationally efficient and accurate model parameter estimation and Bayesian latent-state inference. Online VSMC is capable of performing efficiently, entirely on-the-fly, both parameter estimation and particle proposal adaptation.
  arXiv  Detail & Related papers  (2023-12-19T21:45:38Z)
• Diffusion models for probabilistic programming [56.47577824219207]
  Diffusion Model Variational Inference (DMVI) is a novel method for automated approximate inference in probabilistic programming languages (PPLs) DMVI is easy to implement, allows hassle-free inference in PPLs without the drawbacks of, e.g., variational inference using normalizing flows, and does not make any constraints on the underlying neural network model.
  arXiv  Detail & Related papers  (2023-11-01T12:17:05Z)
• Balanced Training of Energy-Based Models with Adaptive Flow Sampling [13.951904929884618]
  Energy-based models (EBMs) are versatile density estimation models that directly parameterize an unnormalized log density. We propose a new maximum likelihood training algorithm for EBMs that uses a different type of generative model, normalizing flows (NF) Our method fits an NF to an EBM during training so that an NF-assisted sampling scheme provides an accurate gradient for the EBMs at all times.
  arXiv  Detail & Related papers  (2023-06-01T13:58:06Z)
• Detecting and Mitigating Mode-Collapse for Flow-based Sampling of Lattice Field Theories [6.222204646855336]
  We study the consequences of mode-collapse of normalizing flows in the context of lattice field theory. We propose a metric to quantify the degree of mode-collapse and derive a bound on the resulting bias.
  arXiv  Detail & Related papers  (2023-02-27T19:00:22Z)
• Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations [84.42837346400151]
  Estimating counterfactual outcomes over time has the potential to unlock personalized healthcare. Existing causal inference approaches consider regular, discrete-time intervals between observations and treatment decisions. We propose a controllable simulation environment based on a model of tumor growth for a range of scenarios.
  arXiv  Detail & Related papers  (2022-06-16T17:15:15Z)
• Efficient CDF Approximations for Normalizing Flows [64.60846767084877]
  We build upon the diffeomorphic properties of normalizing flows to estimate the cumulative distribution function (CDF) over a closed region. Our experiments on popular flow architectures and UCI datasets show a marked improvement in sample efficiency as compared to traditional estimators.
  arXiv  Detail & Related papers  (2022-02-23T06:11:49Z)
• GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue [95.23775347605923]
  Building on the success of deep learning, Generative Adversarial Networks (GANs) provide a modern approach to learn a probability distribution from observed samples. GANs often suffer from the mode collapse issue where the generator fails to capture all existing modes of the input distribution. We take an information-theoretic approach and maximize a variational lower bound on the entropy of the generated samples to increase their diversity.
  arXiv  Detail & Related papers  (2020-09-24T19:34:37Z)
• Stochastic Normalizing Flows [2.323220706791067]
  We show that normalizing flows can be used to learn the transformation of a simple prior distribution. We derive an efficient training procedure by which both the sampler's and the flow's parameters can be optimized end-to-end. We illustrate the representational power, sampling efficiency and correctness of SNFs on several benchmarks including applications to molecular sampling systems in equilibrium.
  arXiv  Detail & Related papers  (2020-02-16T23:29:32Z)
• Semi-Supervised Learning with Normalizing Flows [54.376602201489995]
  FlowGMM is an end-to-end approach to generative semi supervised learning with normalizing flows. We show promising results on a wide range of applications, including AG-News and Yahoo Answers text data.
  arXiv  Detail & Related papers  (2019-12-30T17:36:33Z)

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.