Theoretical Analysis of Engression and Reverse Markov Engression

• URL: http://arxiv.org/abs/2606.01002v1
• Date: Sun, 31 May 2026 04:37:44 GMT
• Title: Theoretical Analysis of Engression and Reverse Markov Engression
• Abstract summary: In this paper, we establish nonasymptotic convergence bounds for Engression by directly controlling the Energy Distance between the learned and target conditional distributions.<n>For the Reverse Markov framework, we further develop an Energy-Distance-based chain rule that enables a rigorous analysis of error propagation across reverse steps.<n>Our analysis yields corresponding excess-risk bounds that are near-optimal up to logarithmic factors relative to the classical minimax rate over a general Hlder class.
• Score: 5.917342834515065
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Engression is a recently proposed and effective framework for conditional distribution learning. Its multi-step Reverse Markov extension further improves generative flexibility by decomposing complex conditional sampling into sequential reverse transitions. Despite their strong empirical performance, rigorous finite-sample statistical guarantees for these methods remain unavailable. In this paper, under deep neural network parameterizations, we establish nonasymptotic convergence bounds for Engression by directly controlling the Energy Distance between the learned and target conditional distributions. For the Reverse Markov framework, we further develop an Energy-Distance-based chain rule that enables a rigorous analysis of error propagation across reverse steps. Our analysis yields corresponding excess-risk bounds that are near-optimal up to logarithmic factors relative to the classical minimax rate over a general Hölder class.

Related papers

• Out-of-Distribution generalization of quantile regression with heavy tailed inputs: an SVM approach [2.135617967945777]
  We propose a novel Support Vector Machine (SVM) framework for extreme quantile regression.<n>We establish finite-sample learning guarantees under mild regularity assumptions.<n>We complement our theoretical findings with an empirical study on river flow data from the Danube.
  arXiv  Detail & Related papers  (2026-05-29T18:52:13Z)
• Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization [66.08522228989634]
  We establish the first global convergence result of neural networks for two stage least squares (2SLS) approach in nonparametric instrumental variable regression (NPIV)<n>This is achieved by adopting a lifted perspective through mean-field Langevin dynamics (MFLD)
  arXiv  Detail & Related papers  (2025-11-18T17:51:17Z)
• Neural Optimal Transport Meets Multivariate Conformal Prediction [58.43397908730771]
  We propose a framework for conditional vectorile regression (CVQR)<n>CVQR combines neural optimal transport with quantized optimization, and apply it to predictions.
  arXiv  Detail & Related papers  (2025-09-29T19:50:19Z)
• Uncertainty quantification for Markov chain induced martingales with application to temporal difference learning [55.197497603087065]
  We analyze the performance of the Temporal Difference (TD) learning algorithm with linear function approximations.<n>We establish novel and general high-dimensional concentration inequalities and Berry-Esseen bounds for vector-valued martingales induced by Markov chains.
  arXiv  Detail & Related papers  (2025-02-19T15:33:55Z)
• Unveiling the Cycloid Trajectory of EM Iterations in Mixed Linear Regression [5.883916678819683]
  We study the trajectory of iterations and the convergence rates of the Expectation-Maximization (EM) algorithm for two-component Mixed Linear Regression (2MLR) Recent results have established the super-linear convergence of EM for 2MLR in the noiseless and high SNR settings.
  arXiv  Detail & Related papers  (2024-05-28T14:46:20Z)
• Out-of-distribution robustness for multivariate analysis via causal regularisation [4.487663958743944]
  We propose a regularisation strategy rooted in causality that ensures robustness against distribution shifts.<n>Building upon the anchor regression framework, we demonstrate how incorporating a straightforward regularisation term into the loss function of classical algorithms.<n>Our framework allows users to efficiently verify the compatibility of a loss function with the regularisation strategy.
  arXiv  Detail & Related papers  (2024-03-04T09:21:10Z)
• Errors-in-variables Fr\'echet Regression with Low-rank Covariate Approximation [2.1756081703276]
  Fr'echet regression has emerged as a promising approach for regression analysis involving non-Euclidean response variables. Our proposed framework combines the concepts of global Fr'echet regression and principal component regression, aiming to improve the efficiency and accuracy of the regression estimator.
  arXiv  Detail & Related papers  (2023-05-16T08:37:54Z)
• Vector-Valued Least-Squares Regression under Output Regularity Assumptions [73.99064151691597]
  We propose and analyse a reduced-rank method for solving least-squares regression problems with infinite dimensional output. We derive learning bounds for our method, and study under which setting statistical performance is improved in comparison to full-rank method.
  arXiv  Detail & Related papers  (2022-11-16T15:07:00Z)
• Optimal variance-reduced stochastic approximation in Banach spaces [114.8734960258221]
  We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. We establish non-asymptotic bounds for both the operator defect and the estimation error.
  arXiv  Detail & Related papers  (2022-01-21T02:46:57Z)
• On the Convergence of Stochastic Extragradient for Bilinear Games with Restarted Iteration Averaging [96.13485146617322]
  We present an analysis of the ExtraGradient (SEG) method with constant step size, and present variations of the method that yield favorable convergence. We prove that when augmented with averaging, SEG provably converges to the Nash equilibrium, and such a rate is provably accelerated by incorporating a scheduled restarting procedure.
  arXiv  Detail & Related papers  (2021-06-30T17:51:36Z)
• Towards Understanding Generalization via Decomposing Excess Risk Dynamics [13.4379473119565]
  We analyze the generalization dynamics to derive algorithm-dependent bounds, e.g., stability. Inspired by the observation that neural networks show a slow convergence rate when fitting noise, we propose decomposing the excess risk dynamics. Under the decomposition framework, the new bound accords better with the theoretical and empirical evidence compared to the stability-based bound and uniform convergence bound.
  arXiv  Detail & Related papers  (2021-06-11T03:42:45Z)

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.