Sampling non-log-concave densities via Hessian-free high-resolution dynamics

• URL: http://arxiv.org/abs/2601.02725v1
• Date: Tue, 06 Jan 2026 05:38:09 GMT
• Title: Sampling non-log-concave densities via Hessian-free high-resolution dynamics
• Abstract summary: We study the problem of sampling from a target distribution $(q)prop e-U(q) of the Hessian-free-resolution (HFHR) process.<n>We show that, under an additional assumption that $blana U$ linear growth has at infinity, the contraction for HFHR dynamics is strictly better than that KLD is.
• Score: 8.014749318189851
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the problem of sampling from a target distribution $π(q)\propto e^{-U(q)}$ on $\mathbb{R}^d$, where $U$ can be non-convex, via the Hessian-free high-resolution (HFHR) dynamics, which is a second-order Langevin-type process that has $e^{-U(q)-\frac12|p|^2}$ as its unique invariant distribution, and it reduces to kinetic Langevin dynamics (KLD) as the resolution parameter $α\to0$. The existing theory for HFHR dynamics in the literature is restricted to strongly-convex $U$, although numerical experiments are promising for non-convex settings as well. We focus on studying the convergence of HFHR dynamics when $U$ can be non-convex, which bridges a gap between theory and practice. Under a standard assumption of dissipativity and smoothness on $U$, we adopt the reflection/synchronous coupling method. This yields a Lyapunov-weighted Wasserstein distance in which the HFHR semigroup is exponentially contractive for all sufficiently small $α>0$ whenever KLD is. We further show that, under an additional assumption that asymptotically $\nabla U$ has linear growth at infinity, the contraction rate for HFHR dynamics is strictly better than that of KLD, with an explicit gain. As a case study, we verify the assumptions and the resulting acceleration for three examples: a multi-well potential, Bayesian linear regression with $L^p$ regularizer and Bayesian binary classification. We conduct numerical experiments based on these examples, as well as an additional example of Bayesian logistic regression with real data processed by the neural networks, which illustrates the efficiency of the algorithms based on HFHR dynamics and verifies the acceleration and superior performance compared to KLD.

Related papers

• Improved Analysis for Hessian-free High-resolution Monte Carlo Sampling [7.336637417508747]
  Hessian-free high-resolution (HFHR) dynamics augments underdamped Langevin dynamics (ULD)<n>We establish an explicit quantitative contraction rate for HFHR dynamics under a position Poincaré inequality.<n>An adapted time-augmented Poincaré inequality yields an explicit rate that improves upon the contraction rate of the Langevin dynamics.
  arXiv  Detail & Related papers  (2026-08-25T18:42:23Z)
• Statistical inverse learning and $\ell^1$-regularization [0.27998963147546135]
  We study the recovery of sparse functions from finite, noisy, and indirect observations in the framework of statistical inverse learning.<n>We establish almost-sure exponents and derive non-asymptotic high-probability convergence rates in both prediction and $ell1$ reconstruction norms.
  arXiv  Detail & Related papers  (2026-07-08T14:32:08Z)
• Reflected diffusion models adapt to low-dimensional data [1.4273866043218157]
  This paper provides a statistical analysis of reflected diffusion models on the hypercube $[0,1]D$ supported on $d$-dimensional linear subspaces.<n>By employing an easily implementable infinite series expansion of the transition densities, we develop analytic tools to bound the score function and its approximation by sparse ReLU networks.
  arXiv  Detail & Related papers  (2026-03-25T16:37:33Z)
• Wiener Chaos Expansion based Neural Operator for Singular Stochastic Partial Differential Equations [58.188204772101756]
  This paper explores how our recently developed Wiener Chaos Expansion (WCE)-based neural operator (NO) can be applied to singular partial differential equations.<n>We leverage feature-wise linear modulation (FiLM) to appropriately capture the dependency between the solution of singular SPDE and its smooth remainder.<n>The resulting WCE-FiLM-NO shows excellent performance on $boldsymbol4$, as measured by relative $L$ loss, out-of-distribution and autocorrelation score.
  arXiv  Detail & Related papers  (2026-03-09T10:50:30Z)
• Quantitative Convergence of Wasserstein Gradient Flows of Kernel Mean Discrepancies [10.511277414974613]
  We study the quantitative convergence of Wasserstein gradient flows of Kernel Mean Discrepancy functionals.<n>Our setting covers in particular the training dynamics of shallow neural networks in the infinite-width and continuous time limit.
  arXiv  Detail & Related papers  (2026-03-02T15:32:54Z)
• Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration [67.12978375116599]
  We show that the steps of gradient descent (GD) reduce to those of generalized perceptron algorithms.<n>This helps explain the optimization dynamics and the implicit acceleration phenomenon observed in neural networks.
  arXiv  Detail & Related papers  (2025-12-12T14:16:35Z)
• Renormalizable Spectral-Shell Dynamics as the Origin of Neural Scaling Laws [2.779943773196378]
  We show that deep-network training obeys a simple macroscopic structure despite highly nonlinear optimization dynamics.<n>For mean-squared error loss, the training error evolves as $dot e_t=-M(t)e_t$ with $M(t)=J_(t)J_(t)!*$, a time-dependent self-adjoint operator induced by the network Jacobian.<n>This framework explains neural scaling laws and double descent, and unifies lazy (NTK-like) training and feature learning as two limits of the same spectral-shell
  arXiv  Detail & Related papers  (2025-12-11T08:38:46Z)
• On the Wasserstein Convergence and Straightness of Rectified Flow [54.580605276017096]
  Rectified Flow (RF) is a generative model that aims to learn straight flow trajectories from noise to data.<n>We provide a theoretical analysis of the Wasserstein distance between the sampling distribution of RF and the target distribution.<n>We present general conditions guaranteeing uniqueness and straightness of 1-RF, which is in line with previous empirical findings.
  arXiv  Detail & Related papers  (2024-10-19T02:36:11Z)
• Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models [49.81937966106691]
  We develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models. In contrast to prior works, our theory is developed based on an elementary yet versatile non-asymptotic approach.
  arXiv  Detail & Related papers  (2023-06-15T16:30:08Z)
• Efficient quantum algorithm for nonlinear reaction-diffusion equations and energy estimation [5.576305273694895]
  We develop an efficient quantum algorithm based on [1] for a class of nonlinear partial differential equations (PDEs) We show how to estimate the mean square kinetic energy in the solution by postprocessing the quantum state that encodes it to extract derivative information. As applications, we consider the Fisher-KPP and Allen-Cahn equations, which have interpretations in classical physics.
  arXiv  Detail & Related papers  (2022-05-02T18:15:32Z)
• Convex Analysis of the Mean Field Langevin Dynamics [49.66486092259375]
  convergence rate analysis of the mean field Langevin dynamics is presented. $p_q$ associated with the dynamics allows us to develop a convergence theory parallel to classical results in convex optimization.
  arXiv  Detail & Related papers  (2022-01-25T17:13:56Z)
• Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks [0.0]
  We study the dynamics of a neural network in function space when optimizing the mean squared error via gradient flow. We show that the network learns eigenfunctions of an integral operator $T_Kinfty$ determined by the Neural Tangent Kernel (NTK) We conclude that damped deviations offers a simple and unifying perspective of the dynamics when optimizing the squared error.
  arXiv  Detail & Related papers  (2022-01-12T23:28:41Z)
• An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap [66.75488143823337]
  We show that an exponential sample complexity lower bound still holds even if a constant suboptimality gap is assumed. Perhaps surprisingly, this implies an exponential separation between the online RL setting and the generative model setting.
  arXiv  Detail & Related papers  (2021-03-23T17:05:54Z)
• Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave Sampling [110.88857917726276]
  We provide a new convergence analysis of gradient Langevin dynamics (SGLD) for sampling from a class of distributions that can be non-log-concave. At the core of our approach is a novel conductance analysis of SGLD using an auxiliary time-reversible Markov Chain.
  arXiv  Detail & Related papers  (2020-10-19T15:23:18Z)
• Cumulant GAN [17.4556035872983]
  We propose a novel loss function for training Generative Adversarial Networks (GANs) We show that the corresponding optimization problem is equivalent to R'enyi divergence minimization. We experimentally demonstrate that image generation is more robust relative to Wasserstein GAN.
  arXiv  Detail & Related papers  (2020-06-11T17:23:02Z)
• Gravitational-wave parameter estimation with autoregressive neural network flows [0.0]
  We introduce the use of autoregressive normalizing flows for rapid likelihood-free inference of binary black hole system parameters from gravitational-wave data with deep neural networks. A normalizing flow is an invertible mapping on a sample space that can be used to induce a transformation from a simple probability distribution to a more complex one. We build a more powerful latent variable model by incorporating autoregressive flows within the variational autoencoder framework.
  arXiv  Detail & Related papers  (2020-02-18T15:44:04Z)

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.