Generation Properties of Stochastic Interpolation under Finite Training Set

• URL: http://arxiv.org/abs/2509.21925v1
• Date: Fri, 26 Sep 2025 06:13:03 GMT
• Title: Generation Properties of Stochastic Interpolation under Finite Training Set
• Authors: Yunchen Li, Shaohui Lin, Zhou Yu,
• Abstract summary: Under some regularity conditions, the deterministic generative process exactly recovers the training samples, while the generative process manifests as training samples with added noise.<n>Our theoretical analysis reveals that, in the presence of estimation errors, the generation process effectively produces convex combinations of training samples corrupted by a mixture of uniform and Gaussian noise.
• Score: 28.505356058958125
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates the theoretical behavior of generative models under finite training populations. Within the stochastic interpolation generative framework, we derive closed-form expressions for the optimal velocity field and score function when only a finite number of training samples are available. We demonstrate that, under some regularity conditions, the deterministic generative process exactly recovers the training samples, while the stochastic generative process manifests as training samples with added Gaussian noise. Beyond the idealized setting, we consider model estimation errors and introduce formal definitions of underfitting and overfitting specific to generative models. Our theoretical analysis reveals that, in the presence of estimation errors, the stochastic generation process effectively produces convex combinations of training samples corrupted by a mixture of uniform and Gaussian noise. Experiments on generation tasks and downstream tasks such as classification support our theory.

Related papers

• Discrete Feynman-Kac Correctors [47.62319930071118]
  We propose a framework that allows for controlling the generated distribution of discrete masked diffusion models at inference time.<n>We derive Sequential Monte Carlo (SMC) algorithms that, given a trained discrete diffusion model, control the temperature of the sampled distribution.<n>We illustrate the utility of our framework in several applications including: efficient sampling from the Boltzmann distribution of the Ising model, improving the performance of language models for code generation and amortized learning, as well as reward-tilted protein sequence generation.
  arXiv  Detail & Related papers  (2026-01-15T13:55:38Z)
• Neural Jump ODEs as Generative Models [2.528513413370073]
  We explore how Neural Jump ODEs (NJODEs) can be used as generative models for Ito processes.<n>Given (discrete observations of) samples of a fixed underlying Ito process, the NJODE framework can be used to approximate the drift and diffusion coefficients of the process.
  arXiv  Detail & Related papers  (2025-10-03T06:43:12Z)
• When and how can inexact generative models still sample from the data manifold? [2.4664553878979185]
  Despite learning errors in the score function or the drift vector field, the generated samples appear to shift emphalong the support of the data distribution but not emphaway from it.<n>We show that the alignment of the top Lyapunov vectors with the tangent spaces along the boundary of the data manifold leads to robustness.
  arXiv  Detail & Related papers  (2025-08-11T03:24:34Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts [64.34482582690927]
  We provide an efficient and principled method for sampling from a sequence of annealed, geometric-averaged, or product distributions derived from pretrained score-based models.<n>We propose Sequential Monte Carlo (SMC) resampling algorithms that leverage inference-time scaling to improve sampling quality.
  arXiv  Detail & Related papers  (2025-03-04T17:46:51Z)
• May the Noise be with you: Adversarial Training without Adversarial Examples [3.4673556247932225]
  We investigate the question: Can we obtain adversarially-trained models without training on adversarial? Our proposed approach incorporates inherentity by embedding Gaussian noise within the layers of the NN model at training time. Our work contributes adversarially trained networks using a completely different approach, with empirically similar robustness to adversarial training.
  arXiv  Detail & Related papers  (2023-12-12T08:22:28Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• Diffusing Gaussian Mixtures for Generating Categorical Data [21.43283907118157]
  We propose a generative model for categorical data based on diffusion models with a focus on high-quality sample generation. Our method of evaluation highlights the capabilities and limitations of different generative models for generating categorical data.
  arXiv  Detail & Related papers  (2023-03-08T14:55:32Z)
• Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion [2.2849153854336763]
  temporal data can be viewed as discretized measurements of the underlying function. To build a generative model for such data we have to model the process that governs it. We propose a solution by defining the denoising diffusion model in the function space.
  arXiv  Detail & Related papers  (2022-11-04T17:02:01Z)
• On the Inherent Regularization Effects of Noise Injection During Training [12.614901374282868]
  We present a theoretical study of one particular way of random perturbation, which corresponds to injecting artificial noise to the training data. We provide a precise characterization of the training and generalization errors of such randomly perturbed learning problems on a random feature model.
  arXiv  Detail & Related papers  (2021-02-15T07:43:18Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)
• Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation [51.091890311312085]
  We propose a new training scheme for auto-regressive sequence generative models, which is effective and stable when operating at large sample space encountered in text generation. Our method stably outperforms Maximum Likelihood Estimation and other state-of-the-art sequence generative models in terms of both quality and diversity.
  arXiv  Detail & Related papers  (2020-07-12T15:31:24Z)
• Efficiently Sampling Functions from Gaussian Process Posteriors [76.94808614373609]
  We propose an easy-to-use and general-purpose approach for fast posterior sampling. We demonstrate how decoupled sample paths accurately represent Gaussian process posteriors at a fraction of the usual cost.
  arXiv  Detail & Related papers  (2020-02-21T14:03:16Z)

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.