Augmented Bridge Matching
- URL: http://arxiv.org/abs/2311.06978v1
- Date: Sun, 12 Nov 2023 22:42:34 GMT
- Title: Augmented Bridge Matching
- Authors: Valentin De Bortoli, Guan-Horng Liu, Tianrong Chen, Evangelos A.
Theodorou, Weilie Nie
- Abstract summary: Flow and bridge matching processes can interpolate between arbitrary data distributions.
We show that a simple modification of the matching process recovers this coupling by augmenting the velocity field.
We illustrate the efficiency of our augmentation in learning mixture of image translation tasks.
- Score: 32.668433085737036
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Flow and bridge matching are a novel class of processes which encompass
diffusion models. One of the main aspect of their increased flexibility is that
these models can interpolate between arbitrary data distributions i.e. they
generalize beyond generative modeling and can be applied to learning stochastic
(and deterministic) processes of arbitrary transfer tasks between two given
distributions. In this paper, we highlight that while flow and bridge matching
processes preserve the information of the marginal distributions, they do
\emph{not} necessarily preserve the coupling information unless additional,
stronger optimality conditions are met. This can be problematic if one aims at
preserving the original empirical pairing. We show that a simple modification
of the matching process recovers this coupling by augmenting the velocity field
(or drift) with the information of the initial sample point. Doing so, we lose
the Markovian property of the process but preserve the coupling information
between distributions. We illustrate the efficiency of our augmentation in
learning mixture of image translation tasks.
Related papers
- Generative Assignment Flows for Representing and Learning Joint Distributions of Discrete Data [2.6499018693213316]
We introduce a novel generative model for the representation of joint probability distributions of a possibly large number of discrete random variables.
The embedding of the flow via the Segre map in the meta-simplex of all discrete joint distributions ensures that any target distribution can be represented in principle.
Our approach has strong motivation from first principles of modeling coupled discrete variables.
arXiv Detail & Related papers (2024-06-06T21:58:33Z) - InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion [53.90516061351706]
We present InterHandGen, a novel framework that learns the generative prior of two-hand interaction.
For sampling, we combine anti-penetration and synthesis-free guidance to enable plausible generation.
Our method significantly outperforms baseline generative models in terms of plausibility and diversity.
arXiv Detail & Related papers (2024-03-26T06:35:55Z) - Theoretical Insights for Diffusion Guidance: A Case Study for Gaussian
Mixture Models [59.331993845831946]
Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties.
This paper provides the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models.
arXiv Detail & Related papers (2024-03-03T23:15:48Z) - Selective Mixup Helps with Distribution Shifts, But Not (Only) because
of Mixup [26.105340203096596]
We show that non-random selection of pairs affects the training distribution and improve generalization by means completely unrelated to the mixing.
We have found a new equivalence between two successful methods: selective mixup and resampling.
arXiv Detail & Related papers (2023-05-26T10:56:22Z) - Structural Pruning for Diffusion Models [65.02607075556742]
We present Diff-Pruning, an efficient compression method tailored for learning lightweight diffusion models from pre-existing ones.
Our empirical assessment, undertaken across several datasets highlights two primary benefits of our proposed method.
arXiv Detail & Related papers (2023-05-18T12:38:21Z) - Improving Fair Training under Correlation Shifts [33.385118640843416]
In particular, when the bias between labels and sensitive groups changes, the fairness of the trained model is directly influenced and can worsen.
We analytically show that existing in-processing fair algorithms have fundamental limits in accuracy and group fairness.
We propose a novel pre-processing step that samples the input data to reduce correlation shifts.
arXiv Detail & Related papers (2023-02-05T07:23:35Z) - Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence
Embedding [51.48582649050054]
We propose a representation normalization method which aims at disentangling the correlations between features of encoded sentences.
We also propose Kernel-Whitening, a Nystrom kernel approximation method to achieve more thorough debiasing on nonlinear spurious correlations.
Experiments show that Kernel-Whitening significantly improves the performance of BERT on out-of-distribution datasets while maintaining in-distribution accuracy.
arXiv Detail & Related papers (2022-10-14T05:56:38Z) - Contrastive learning of strong-mixing continuous-time stochastic
processes [53.82893653745542]
Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data.
We show that a properly constructed contrastive learning task can be used to estimate the transition kernel for small-to-mid-range intervals in the diffusion case.
arXiv Detail & Related papers (2021-03-03T23:06:47Z) - Variational Mixture of Normalizing Flows [0.0]
Deep generative models, such as generative adversarial networks autociteGAN, variational autoencoders autocitevaepaper, and their variants, have seen wide adoption for the task of modelling complex data distributions.
Normalizing flows have overcome this limitation by leveraging the change-of-suchs formula for probability density functions.
The present work overcomes this by using normalizing flows as components in a mixture model and devising an end-to-end training procedure for such a model.
arXiv Detail & Related papers (2020-09-01T17:20:08Z) - Robust model training and generalisation with Studentising flows [22.757298187704745]
We discuss how these methods can be further improved based on insights from robust (in particular, resistant) statistics.
We propose to endow flow-based models with fat-tailed latent distributions as a simple drop-in replacement for the Gaussian distribution.
Experiments on several different datasets confirm the efficacy of the proposed approach.
arXiv Detail & Related papers (2020-06-11T16:47:01Z) - Embedding Propagation: Smoother Manifold for Few-Shot Classification [131.81692677836202]
We propose to use embedding propagation as an unsupervised non-parametric regularizer for manifold smoothing in few-shot classification.
We empirically show that embedding propagation yields a smoother embedding manifold.
We show that embedding propagation consistently improves the accuracy of the models in multiple semi-supervised learning scenarios by up to 16% points.
arXiv Detail & Related papers (2020-03-09T13:51:09Z)
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.