MCMC Variational Inference via Uncorrected Hamiltonian Annealing

• URL: http://arxiv.org/abs/2107.04150v1
• Date: Thu, 8 Jul 2021 23:59:45 GMT
• Title: MCMC Variational Inference via Uncorrected Hamiltonian Annealing
• Authors: Tomas Geffner and Justin Domke
• Abstract summary: We propose a framework to use an AIS-like procedure with Uncorrected Hamiltonian MCMC. Our method leads to tight and differentiable lower bounds on log Z.
• Score: 42.26118870861363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Given an unnormalized target distribution we want to obtain approximate samples from it and a tight lower bound on its (log) normalization constant log Z. Annealed Importance Sampling (AIS) with Hamiltonian MCMC is a powerful method that can be used to do this. Its main drawback is that it uses non-differentiable transition kernels, which makes tuning its many parameters hard. We propose a framework to use an AIS-like procedure with Uncorrected Hamiltonian MCMC, called Uncorrected Hamiltonian Annealing. Our method leads to tight and differentiable lower bounds on log Z. We show empirically that our method yields better performances than other competing approaches, and that the ability to tune its parameters using reparameterization gradients may lead to large performance improvements.

Related papers

• Moreau Envelope ADMM for Decentralized Weakly Convex Optimization [55.2289666758254]
  This paper proposes a proximal variant of the alternating direction method of multipliers (ADMM) for distributed optimization. The results of our numerical experiments indicate that our method is faster and more robust than widely-used approaches.
  arXiv  Detail & Related papers  (2023-08-31T14:16:30Z)
• Optimization of Annealed Importance Sampling Hyperparameters [77.34726150561087]
  Annealed Importance Sampling (AIS) is a popular algorithm used to estimates the intractable marginal likelihood of deep generative models. We present a parameteric AIS process with flexible intermediary distributions and optimize the bridging distributions to use fewer number of steps for sampling. We assess the performance of our optimized AIS for marginal likelihood estimation of deep generative models and compare it to other estimators.
  arXiv  Detail & Related papers  (2022-09-27T07:58:25Z)
• 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)
• Scalable Variational Gaussian Processes via Harmonic Kernel Decomposition [54.07797071198249]
  We introduce a new scalable variational Gaussian process approximation which provides a high fidelity approximation while retaining general applicability. We demonstrate that, on a range of regression and classification problems, our approach can exploit input space symmetries such as translations and reflections. Notably, our approach achieves state-of-the-art results on CIFAR-10 among pure GP models.
  arXiv  Detail & Related papers  (2021-06-10T18:17:57Z)
• Machine Learning and Variational Algorithms for Lattice Field Theory [1.198562319289569]
  In lattice quantum field theory studies, parameters defining the lattice theory must be tuned toward criticality to access continuum physics. We introduce an approach to "deform" Monte Carlo estimators based on contour deformations applied to the domain of the path integral. We demonstrate that flow-based MCMC can mitigate critical slowing down and observifolds can exponentially reduce variance in proof-of-principle applications.
  arXiv  Detail & Related papers  (2021-06-03T16:37:05Z)
• Tighter Bounds on the Log Marginal Likelihood of Gaussian Process Regression Using Conjugate Gradients [19.772149500352945]
  We show that approximate maximum likelihood learning of model parameters by maximising our lower bound retains many of the sparse variational approach benefits. In experiments, we show improved predictive performance with our model for a comparable amount of training time compared to other conjugate gradient based approaches.
  arXiv  Detail & Related papers  (2021-02-16T17:54:59Z)
• On Batch Normalisation for Approximate Bayesian Inference [102.94525205971873]
  We show that batch-normalisation does not affect the optimum of the evidence lower bound (ELBO) We also study the Monte Carlo Batch Normalisation (MCBN) algorithm, proposed as an approximate inference technique parallel to MC Dropout.
  arXiv  Detail & Related papers  (2020-12-24T12:40:11Z)
• Optimal Thinning of MCMC Output [18.177473712344565]
  We consider the problem of retrospectively selecting a subset of states, of fixed cardinality, from the sample path. A novel method is proposed, based on greedy minimisation of a kernel discrepancy, that is suitable for problems where heavy compression is required.
  arXiv  Detail & Related papers  (2020-05-08T10:54:25Z)

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.