Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization

• URL: http://arxiv.org/abs/2002.05465v4
• Date: Sun, 28 Jan 2024 12:29:57 GMT
• Title: Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization
• Abstract summary: We provide a nonasymotic analysis of the convergence of the Hamiltonian Monte Carlo to a target measure in a gradient under local conditions. We prove that the SGHMC can provide high-precision results uniformly in the number of iterations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We provide a nonasymptotic analysis of the convergence of the stochastic gradient Hamiltonian Monte Carlo (SGHMC) to a target measure in Wasserstein-2 distance without assuming log-concavity. Our analysis quantifies key theoretical properties of the SGHMC as a sampler under local conditions which significantly improves the findings of previous results. In particular, we prove that the Wasserstein-2 distance between the target and the law of the SGHMC is uniformly controlled by the step-size of the algorithm, therefore demonstrate that the SGHMC can provide high-precision results uniformly in the number of iterations. The analysis also allows us to obtain nonasymptotic bounds for nonconvex optimization problems under local conditions and implies that the SGHMC, when viewed as a nonconvex optimizer, converges to a global minimum with the best known rates. We apply our results to obtain nonasymptotic bounds for scalable Bayesian inference and nonasymptotic generalization bounds.

Related papers

• The Role of Gradient Modification in Heavy-Tailed Nonconvex Stochastic Min-Max Optimization [50.59470683896735]
  min-max optimization has attracted increasing attention due to its applications in modern machine learning.<n>We provide a comprehensive theoretical of gradient descent (SGDA)<n>We develop new clipping-free algorithms, i.e., Stoc-GDAM and Stoc-TRmax, and they both can achieve the optimal dependence on the target accuracy without using gradient clipping.
  arXiv  Detail & Related papers  (2026-09-05T12:49:28Z)
• Tamed Stochastic Gradient Hamiltonian Monte Carlo [6.75602425917782]
  We propose a novel tamed gradient Hamiltonian Monte Carlo (tSGHMC) algorithm for sampling and optimization problems with superlinearly growing gradients.<n>We show that tSGHMC achieves lower root mean square error and expected excess risk across a range of tasks.
  arXiv  Detail & Related papers  (2026-07-16T11:36:00Z)
• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• A semiconcavity approach to stability of entropic plans and exponential convergence of Sinkhorn's algorithm [3.686530147760242]
  We study stability of bounds and convergence of Sinkhorn's algorithm for the entropic optimal transport problem.<n>New applications include subspace elastic costs, weakly log-concave marginals, marginals with light tails.
  arXiv  Detail & Related papers  (2024-12-12T12:45:31Z)
• Non-asymptotic convergence analysis of the stochastic gradient Hamiltonian Monte Carlo algorithm with discontinuous stochastic gradient with applications to training of ReLU neural networks [8.058385158111207]
  We provide a non-asymptotic analysis of the convergence of the gradient Hamiltonian Monte Carlo to a target measure in Wasserstein-1 and Wasserstein-2 distance. To illustrate our main results, we consider numerical experiments on quantile estimation and on several problems involving ReLU neural networks relevant in finance and artificial intelligence.
  arXiv  Detail & Related papers  (2024-09-25T17:21:09Z)
• Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds [77.4346324549323]
  We show that a step size agnostic to the curvature of the manifold achieves a curvature-independent and linear last-iterate convergence rate. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence has not been considered before.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• Convex and Non-convex Optimization Under Generalized Smoothness [69.69521650503431]
  An analysis of convex and non- optimization methods often requires the Lipsitzness gradient, which limits the analysis by this trajectorys. Recent work generalizes the gradient setting via the non-uniform smoothness condition.
  arXiv  Detail & Related papers  (2023-06-02T04:21:59Z)
• Kinetic Langevin MCMC Sampling Without Gradient Lipschitz Continuity -- the Strongly Convex Case [0.0]
  We consider sampling from log concave distributions in Hamiltonian setting, without assuming that the objective is globally Lipschitz. We propose two algorithms based on polygonal gradient (tamed) Euler schemes, to sample from a target measure, and provide non-asymptotic 2-Wasserstein distance bounds between the law of the process of each algorithm and the target measure.
  arXiv  Detail & Related papers  (2023-01-19T12:32:41Z)
• Nonconvex Stochastic Scaled-Gradient Descent and Generalized Eigenvector Problems [98.34292831923335]
  Motivated by the problem of online correlation analysis, we propose the emphStochastic Scaled-Gradient Descent (SSD) algorithm. We bring these ideas together in an application to online correlation analysis, deriving for the first time an optimal one-time-scale algorithm with an explicit rate of local convergence to normality.
  arXiv  Detail & Related papers  (2021-12-29T18:46:52Z)
• Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo [60.785586069299356]
  This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance. Our theoretical analysis is further validated by numerical experiments.
  arXiv  Detail & Related papers  (2021-09-08T18:00:05Z)
• Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
  Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
  arXiv  Detail & Related papers  (2021-07-21T17:10:14Z)
• Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity [49.66890309455787]
  We introduce the expected co-coercivity condition, explain its benefits, and provide the first last-iterate convergence guarantees of SGDA and SCO. We prove linear convergence of both methods to a neighborhood of the solution when they use constant step-size. Our convergence guarantees hold under the arbitrary sampling paradigm, and we give insights into the complexity of minibatching.
  arXiv  Detail & Related papers  (2021-06-30T18:32:46Z)
• Better Theory for SGD in the Nonconvex World [2.6397379133308214]
  Large-scale non optimization problems are ubiquitous in modern machine learning. We perform experiments on the effects of a wide array of synthetic minibatch sizes on the Gradient Descent (SG) problem.
  arXiv  Detail & Related papers  (2020-02-09T09:56:06Z)

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.