KL-geodesics flow matching with a novel sampling scheme

• URL: http://arxiv.org/abs/2411.16821v4
• Date: Tue, 25 Mar 2025 09:09:07 GMT
• Title: KL-geodesics flow matching with a novel sampling scheme
• Authors: Egor Sevriugov, Ivan Oseledets,
• Abstract summary: Non-autoregressive language models generate all tokens simultaneously, offering potential speed advantages over traditional autoregressive models.<n>We investigate a conditional flow matching approach for text generation.
• Score: 4.347494885647007
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Non-autoregressive language models generate all tokens simultaneously, offering potential speed advantages over traditional autoregressive models, but they face challenges in modeling the complex dependencies inherent in text data. In this work, we investigate a conditional flow matching approach for text generation. We represent tokens as one-hot vectors in a \(V\)-dimensional simplex and utilize geodesics under the Kullback-Leibler (KL) divergence, which correspond to linear interpolation in logit space. We provide a theoretical justification that maximizing the conditional likelihood \(P_{\theta}(x_1 \mid x_t, t)\) yields the exact flow matching velocity under logit interpolation. To address the suboptimal performance of basic inference, we propose a novel empirical sampling scheme that iteratively samples from the conditional distribution and introduces additional noise, significantly improving results despite lacking full theoretical underpinnings. Furthermore, we propose a hybrid inference method that combines the basic approach with the sampling scheme. This method demonstrates superior performance on both conditional and unconditional text generation experiments compared to previous SOTA method for discrete flow matching.

Related papers

• Parallel simulation for sampling under isoperimetry and score-based diffusion models [56.39904484784127]
  As data size grows, reducing the iteration cost becomes an important goal. Inspired by the success of the parallel simulation of the initial value problem in scientific computation, we propose parallel Picard methods for sampling tasks. Our work highlights the potential advantages of simulation methods in scientific computation for dynamics-based sampling and diffusion models.
  arXiv  Detail & Related papers  (2024-12-10T11:50:46Z)
• Simulation-Free Training of Neural ODEs on Paired Data [20.36333430055869]
  We employ the flow matching framework for simulation-free training of NODEs. We show that applying flow matching directly between paired data can often lead to an ill-defined flow. We propose a simple extension that applies flow matching in the embedding space of data pairs.
  arXiv  Detail & Related papers  (2024-10-30T11:18:27Z)
• Generalization error of min-norm interpolators in transfer learning [2.7309692684728617]
  Min-norm interpolators emerge naturally as implicit regularized limits of modern machine learning algorithms. In many applications, a limited amount of test data may be available during training, yet properties of min-norm in this setting are not well-understood. We establish a novel anisotropic local law to achieve these characterizations.
  arXiv  Detail & Related papers  (2024-06-20T02:23:28Z)
• On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
  Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
  arXiv  Detail & Related papers  (2024-05-18T15:59:41Z)
• Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
  In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
  arXiv  Detail & Related papers  (2024-01-29T02:08:40Z)
• Generative Modeling with Phase Stochastic Bridges [49.4474628881673]
  Diffusion models (DMs) represent state-of-the-art generative models for continuous inputs. We introduce a novel generative modeling framework grounded in textbfphase space dynamics Our framework demonstrates the capability to generate realistic data points at an early stage of dynamics propagation.
  arXiv  Detail & Related papers  (2023-10-11T18:38:28Z)
• DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models [58.450152413700586]
  We introduce a soft absorbing state that facilitates the diffusion model in learning to reconstruct discrete mutations based on the underlying Gaussian space. We employ state-of-the-art ODE solvers within the continuous space to expedite the sampling process. Our proposed method effectively accelerates the training convergence by 4x and generates samples of similar quality 800x faster.
  arXiv  Detail & Related papers  (2023-10-09T15:29:10Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
  Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs) GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations. We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
  arXiv  Detail & Related papers  (2023-04-22T15:32:59Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• Sequential Ensembling for Semantic Segmentation [4.030520171276982]
  We benchmark the popular ensembling approach of combining predictions of multiple, independently-trained, state-of-the-art models. We propose a novel method inspired by boosting to sequentially ensemble networks that significantly outperforms the naive ensemble baseline.
  arXiv  Detail & Related papers  (2022-10-08T22:13:59Z)
• Structured Optimal Variational Inference for Dynamic Latent Space Models [16.531262817315696]
  We consider a latent space model for dynamic networks, where our objective is to estimate the pairwise inner products plus the intercept of the latent positions. To balance posterior inference and computational scalability, we consider a structured mean-field variational inference framework.
  arXiv  Detail & Related papers  (2022-09-29T22:10:42Z)
• Interpolation-based Correlation Reduction Network for Semi-Supervised Graph Learning [49.94816548023729]
  We propose a novel graph contrastive learning method, termed Interpolation-based Correlation Reduction Network (ICRN) In our method, we improve the discriminative capability of the latent feature by enlarging the margin of decision boundaries. By combining the two settings, we extract rich supervision information from both the abundant unlabeled nodes and the rare yet valuable labeled nodes for discnative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• Dilated Continuous Random Field for Semantic Segmentation [6.1794523510406885]
  Mean field approximation methodology has laid the foundation of modern Continuous Random Field (CRF) based solutions for semantic segmentation. In this paper, we propose to relax the hard constraint of mean field approximation, by a global optimization with the proposed dilated sparse convolution module (DSConv) In addition, adaptive global average-pooling and adaptive global max-pooling are implemented as replacements of fully connected layers.
  arXiv  Detail & Related papers  (2022-02-01T00:38:55Z)
• Towards extraction of orthogonal and parsimonious non-linear modes from turbulent flows [0.0]
  We propose a deep probabilistic-neural-network architecture for learning a minimal and near-orthogonal set of non-linear modes. Our approach is based on $beta$-variational autoencoders ($beta$-VAEs) and convolutional neural networks (CNNs)
  arXiv  Detail & Related papers  (2021-09-03T13:38:51Z)
• Posterior-Aided Regularization for Likelihood-Free Inference [23.708122045184698]
  Posterior-Aided Regularization (PAR) is applicable to learning the density estimator, regardless of the model structure. We provide a unified estimation method of PAR to estimate both reverse KL term and mutual information term with a single neural network.
  arXiv  Detail & Related papers  (2021-02-15T16:59:30Z)
• Efficient Semi-Implicit Variational Inference [65.07058307271329]
  We propose an efficient and scalable semi-implicit extrapolational (SIVI) Our method maps SIVI's evidence to a rigorous inference of lower gradient values.
  arXiv  Detail & Related papers  (2021-01-15T11:39:09Z)
• Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck [52.08901549360262]
  Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. VAEs tend to ignore latent variables with a strong auto-regressive decoder. We propose a principled approach to enforce an implicit latent feature matching in a more compact latent space.
  arXiv  Detail & Related papers  (2020-04-22T14:41:37Z)

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.