Multisample Flow Matching: Straightening Flows with Minibatch Couplings

• URL: http://arxiv.org/abs/2304.14772v2
• Date: Wed, 24 May 2023 18:17:17 GMT
• Title: Multisample Flow Matching: Straightening Flows with Minibatch Couplings
• Authors: Aram-Alexandre Pooladian, Heli Ben-Hamu, Carles Domingo-Enrich, Brandon Amos, Yaron Lipman, and Ricky T. Q. Chen
• Abstract summary: 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.
• Score: 38.82598694134521
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples. Recent works, such as Flow Matching, derived paths that are optimal for each data sample. However, these algorithms rely on independent data and noise samples, and do not exploit underlying structure in the data distribution for constructing probability paths. We propose Multisample Flow Matching, a more general framework that uses non-trivial couplings between data and noise samples while satisfying the correct marginal constraints. At very small overhead costs, this generalization allows us to (i) reduce gradient variance during training, (ii) obtain straighter flows for the learned vector field, which allows us to generate high-quality samples using fewer function evaluations, and (iii) obtain transport maps with lower cost in high dimensions, which has applications beyond generative modeling. Importantly, we do so in a completely simulation-free manner with a simple minimization objective. We show that our proposed methods improve sample consistency on downsampled ImageNet data sets, and lead to better low-cost sample generation.

Related papers

• 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)
• Learning Sampling Distributions for Model Predictive Control [36.82905770866734]
  Sampling-based approaches to Model Predictive Control (MPC) have become a cornerstone of contemporary approaches to MPC. We propose to carry out all operations in the latent space, allowing us to take full advantage of the learned distribution. Specifically, we frame the learning problem as bi-level optimization and show how to train the controller with backpropagation-through-time.
  arXiv  Detail & Related papers  (2022-12-05T20:35:36Z)
• ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data [93.06336507035486]
  Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. We present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks.
  arXiv  Detail & Related papers  (2022-10-27T02:55:15Z)
• Learning from aggregated data with a maximum entropy model [73.63512438583375]
  We show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis. We present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.
  arXiv  Detail & Related papers  (2022-10-05T09:17:27Z)
• POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples [19.311470287767385]
  We propose to use out-of-distribution samples, i.e., unlabeled samples coming from outside the target classes, to improve few-shot learning. Our approach is simple to implement, agnostic to feature extractors, lightweight without any additional cost for pre-training, and applicable to both inductive and transductive settings.
  arXiv  Detail & Related papers  (2022-06-08T18:59:21Z)
• Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach [18.007258270845107]
  We propose LUD-VAE, a deep generative method to learn the joint probability density function from data sampled from marginal distributions. We apply our method to real-world image denoising and super-resolution tasks and train the models using the synthetic data generated by the LUD-VAE.
  arXiv  Detail & Related papers  (2022-04-21T13:27:17Z)
• 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)
• Effective Proximal Methods for Non-convex Non-smooth Regularized Learning [27.775096437736973]
  We show that the independent sampling scheme tends to improve performance of the commonly-used uniform sampling scheme. Our new analysis also derives a speed for the sampling than best one available so far.
  arXiv  Detail & Related papers  (2020-09-14T16:41:32Z)
• Bandit Samplers for Training Graph Neural Networks [63.17765191700203]
  Several sampling algorithms with variance reduction have been proposed for accelerating the training of Graph Convolution Networks (GCNs) These sampling algorithms are not applicable to more general graph neural networks (GNNs) where the message aggregator contains learned weights rather than fixed weights, such as Graph Attention Networks (GAT)
  arXiv  Detail & Related papers  (2020-06-10T12:48:37Z)
• Learning Entangled Single-Sample Distributions via Iterative Trimming [28.839136703139225]
  We analyze a simple and computationally efficient method based on iteratively trimming samples and re-estimating the parameter on the trimmed sample set. We show that the method in logarithmic iterations outputs an estimation whose error only depends on the noise level of the $lceil alpha n rceil$-th noisiest data point.
  arXiv  Detail & Related papers  (2020-04-20T18:37:43Z)

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.