Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution

• URL: http://arxiv.org/abs/2310.16834v3
• Date: Thu, 6 Jun 2024 21:06:44 GMT
• Title: Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
• Authors: Aaron Lou, Chenlin Meng, Stefano Ermon,
• Abstract summary: We propose score entropy as a novel loss that naturally extends score matching to discrete spaces. We test our Score Entropy Discrete Diffusion models on standard language modeling tasks.
• Score: 67.9215891673174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite their groundbreaking performance for many generative modeling tasks, diffusion models have fallen short on discrete data domains such as natural language. Crucially, standard diffusion models rely on the well-established theory of score matching, but efforts to generalize this to discrete structures have not yielded the same empirical gains. In this work, we bridge this gap by proposing score entropy, a novel loss that naturally extends score matching to discrete spaces, integrates seamlessly to build discrete diffusion models, and significantly boosts performance. Experimentally, we test our Score Entropy Discrete Diffusion models (SEDD) on standard language modeling tasks. For comparable model sizes, SEDD beats existing language diffusion paradigms (reducing perplexity by $25$-$75$\%) and is competitive with autoregressive models, in particular outperforming GPT-2. Furthermore, compared to autoregressive mdoels, SEDD generates faithful text without requiring distribution annealing techniques like temperature scaling (around $6$-$8\times$ better generative perplexity than un-annealed GPT-2), can trade compute and quality (similar quality with $32\times$ fewer network evaluations), and enables controllable infilling (matching nucleus sampling quality while enabling other strategies besides left to right prompting).

Related papers

• Energy-Based Diffusion Language Models for Text Generation [126.23425882687195]
  Energy-based Diffusion Language Model (EDLM) is an energy-based model operating at the full sequence level for each diffusion step. Our framework offers a 1.3$times$ sampling speedup over existing diffusion models.
  arXiv  Detail & Related papers  (2024-10-28T17:25:56Z)
• 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)
• Constrained Diffusion Models via Dual Training [80.03953599062365]
  Diffusion processes are prone to generating samples that reflect biases in a training dataset. We develop constrained diffusion models by imposing diffusion constraints based on desired distributions. We show that our constrained diffusion models generate new data from a mixture data distribution that achieves the optimal trade-off among objective and constraints.
  arXiv  Detail & Related papers  (2024-08-27T14:25:42Z)
• Informed Correctors for Discrete Diffusion Models [32.87362154118195]
  We propose a family of informed correctors that more reliably counteracts discretization error by leveraging information learned by the model. We also propose $k$-Gillespie's, a sampling algorithm that better utilizes each model evaluation, while still enjoying the speed and flexibility of $tau$-leaping. Across several real and synthetic datasets, we show that $k$-Gillespie's with informed correctors reliably produces higher quality samples at lower computational cost.
  arXiv  Detail & Related papers  (2024-07-30T23:29:29Z)
• Provable Statistical Rates for Consistency Diffusion Models [87.28777947976573]
  Despite the state-of-the-art performance, diffusion models are known for their slow sample generation due to the extensive number of steps involved. This paper contributes towards the first statistical theory for consistency models, formulating their training as a distribution discrepancy minimization problem.
  arXiv  Detail & Related papers  (2024-06-23T20:34:18Z)
• Transfer Learning for Diffusion Models [43.10840361752551]
  Diffusion models consistently produce high-quality synthetic samples. They can be impractical in real-world applications due to high collection costs or associated risks. This paper introduces the Transfer Guided Diffusion Process (TGDP), a novel approach distinct from conventional finetuning and regularization methods.
  arXiv  Detail & Related papers  (2024-05-27T06:48:58Z)
• Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS [0.0]
  The diffusion model is capable of generating high-quality data through a probabilistic approach. It suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. We propose a speech synthesis model with two discriminators: a diffusion discriminator for learning the distribution of the reverse process and a spectrogram discriminator for learning the distribution of the generated data.
  arXiv  Detail & Related papers  (2023-08-03T07:22:04Z)
• Semi-Implicit Denoising Diffusion Models (SIDDMs) [50.30163684539586]
  Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps. We introduce a novel approach that tackles the problem by matching implicit and explicit factors. We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.
  arXiv  Detail & Related papers  (2023-06-21T18:49:22Z)
• Learning Multivariate CDFs and Copulas using Tensor Factorization [39.24470798045442]
  Learning the multivariate distribution of data is a core challenge in statistics and machine learning. In this work, we aim to learn multivariate cumulative distribution functions (CDFs), as they can handle mixed random variables. We show that any grid sampled version of a joint CDF of mixed random variables admits a universal representation as a naive Bayes model. We demonstrate the superior performance of the proposed model in several synthetic and real datasets and applications including regression, sampling and data imputation.
  arXiv  Detail & Related papers  (2022-10-13T16:18:46Z)

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.