Hamiltonian Monte Carlo with Asymmetrical Momentum Distributions

• URL: http://arxiv.org/abs/2110.12907v1
• Date: Thu, 21 Oct 2021 18:36:19 GMT
• Title: Hamiltonian Monte Carlo with Asymmetrical Momentum Distributions
• Authors: Soumyadip Ghosh, Yingdong Lu, Tomasz Nowicki
• Abstract summary: We present a novel convergence analysis for the Hamiltonian Monte Carlo (HMC) algorithm. We show that plain HMC with asymmetrical momentum distributions breaks a key self-adjointness requirement. We propose a modified version that we call the Alternating Direction HMC (AD-HMC)
• Score: 3.562271099341746
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing rigorous convergence guarantees for the Hamiltonian Monte Carlo (HMC) algorithm use Gaussian auxiliary momentum variables, which are crucially symmetrically distributed. We present a novel convergence analysis for HMC utilizing new analytic and probabilistic arguments. The convergence is rigorously established under significantly weaker conditions, which among others allow for general auxiliary distributions. In our framework, we show that plain HMC with asymmetrical momentum distributions breaks a key self-adjointness requirement. We propose a modified version that we call the Alternating Direction HMC (AD-HMC). Sufficient conditions are established under which AD-HMC exhibits geometric convergence in Wasserstein distance. Numerical experiments suggest that AD-HMC can show improved performance over HMC with Gaussian auxiliaries.

Related papers

• Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory [20.758987791387515]
  This work introduces a novel and efficient Bayesian federated learning algorithm, namely, the Federated Averaging Hamiltonian Monte Carlo (FA-HMC) We establish rigorous convergence guarantees of FA-HMC on non-iid distributed data sets. We show that FA-HMC outperforms the existing Federated Averaging-Langevin Monte Carlo (FA-LD) algorithm.
  arXiv  Detail & Related papers  (2024-07-09T15:10:59Z)
• On Convergence of the Alternating Directions SGHMC Algorithm [2.609441136025819]
  We study convergence rates of Hamiltonian Monte Carlo (HMC) algorithms with leapfrog integration under mild conditions on gradient oracle for the target distribution (SGHMC) Our method extends standard HMC by allowing the use of general auxiliary distributions, which is achieved by a novel procedure of Alternating Directions.
  arXiv  Detail & Related papers  (2024-05-21T18:22:44Z)
• Randomized Physics-Informed Machine Learning for Uncertainty Quantification in High-Dimensional Inverse Problems [49.1574468325115]
  We propose a physics-informed machine learning method for uncertainty quantification in high-dimensional inverse problems. We show analytically and through comparison with Hamiltonian Monte Carlo that the rPICKLE posterior converges to the true posterior given by the Bayes rule.
  arXiv  Detail & Related papers  (2023-12-11T07:33:16Z)
• Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems [78.96969465641024]
  We extend mean-field Langevin dynamics to minimax optimization over probability distributions for the first time with symmetric and provably convergent updates. We also study time and particle discretization regimes and prove a new uniform-in-time propagation of chaos result.
  arXiv  Detail & Related papers  (2023-12-02T13:01:29Z)
• On the convergence of dynamic implementations of Hamiltonian Monte Carlo and No U-Turn Samplers [8.999094822549067]
  We consider a general class of MCMC algorithms we call dynamic HMC. We show that this general framework encompasses NUTS as a particular case. Under conditions similar to the ones existing for HMC, we also show that NUTS is geometrically ergodic.
  arXiv  Detail & Related papers  (2023-07-07T08:44:33Z)
• Simultaneous Transport Evolution for Minimax Equilibria on Measures [48.82838283786807]
  Min-max optimization problems arise in several key machine learning setups, including adversarial learning and generative modeling. In this work we focus instead in finding mixed equilibria, and consider the associated lifted problem in the space of probability measures. By adding entropic regularization, our main result establishes global convergence towards the global equilibrium.
  arXiv  Detail & Related papers  (2022-02-14T02:23:16Z)
• Entropy-based adaptive Hamiltonian Monte Carlo [19.358300726820943]
  Hamiltonian Monte Carlo (HMC) is a popular Markov Chain Monte Carlo (MCMC) algorithm to sample from an unnormalized probability distribution. A leapfrog integrator is commonly used to implement HMC in practice, but its performance can be sensitive to the choice of mass matrix used. We develop a gradient-based algorithm that allows for the adaptation of the mass matrix by encouraging the leapfrog integrator to have high acceptance rates.
  arXiv  Detail & Related papers  (2021-10-27T17:52:55Z)
• 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)
• What Are Bayesian Neural Network Posteriors Really Like? [63.950151520585024]
  We show that Hamiltonian Monte Carlo can achieve significant performance gains over standard and deep ensembles. We also show that deep distributions are similarly close to HMC as standard SGLD, and closer than standard variational inference.
  arXiv  Detail & Related papers  (2021-04-29T15:38:46Z)
• Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting [6.684193501969829]
  Hamiltonian Monte Carlo (HMC) is a Markov chain Monte Carlo approach that exhibits favourable exploration properties in high-dimensional models such as neural networks. We introduce a new integration scheme for split HMC that does not rely on symmetric gradients. Our approach demonstrates HMC as a feasible option when considering inference schemes for large-scale machine learning problems.
  arXiv  Detail & Related papers  (2020-10-14T01:58:34Z)
• A Rigorous Link Between Self-Organizing Maps and Gaussian Mixture Models [78.6363825307044]
  This work presents a mathematical treatment of the relation between Self-Organizing Maps (SOMs) and Gaussian Mixture Models (GMMs) We show that energy-based SOM models can be interpreted as performing gradient descent. This link allows to treat SOMs as generative probabilistic models, giving a formal justification for using SOMs to detect outliers, or for sampling.
  arXiv  Detail & Related papers  (2020-09-24T14:09:04Z)

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.