Mean field initialization of the Annealed Importance Sampling algorithm for an efficient evaluation of the Partition Function of Restricted Boltzmann Machines

• URL: http://arxiv.org/abs/2404.11229v1
• Date: Wed, 17 Apr 2024 10:22:03 GMT
• Title: Mean field initialization of the Annealed Importance Sampling algorithm for an efficient evaluation of the Partition Function of Restricted Boltzmann Machines
• Authors: A. Prat Pou, E. Romero, J. Martí, F. Mazzanti,
• Abstract summary: Annealed Importance Sampling (AIS) is a tool to estimate the partition function of a system. We show that both the quality of the estimation and the cost of the computation can be significantly improved by using a properly selected mean-field starting probability distribution. We conclude that these are good starting points to estimate the partition function with AIS with a relatively low computational cost.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Probabilistic models in physics often require from the evaluation of normalized Boltzmann factors, which in turn implies the computation of the partition function Z. Getting the exact value of Z, though, becomes a forbiddingly expensive task as the system size increases. This problem is also present in probabilistic learning models such as the Restricted Boltzmann Machine (RBM), where the situation is even worse as the exact learning rules implies the computation of Z at each iteration. A possible way to tackle this problem is to use the Annealed Importance Sampling (AIS) algorithm, which provides a tool to stochastically estimate the partition function of the system. So far, the standard application of the AIS algorithm starts from the uniform probability distribution and uses a large number of Monte Carlo steps to obtain reliable estimations of Z following an annealing process. In this work we show that both the quality of the estimation and the cost of the computation can be significantly improved by using a properly selected mean-field starting probability distribution. We perform a systematic analysis of AIS in both small- and large-sized problems, and compare the results to exact values in problems where these are known. As a result of our systematic analysis, we propose two successful strategies that work well in all the problems analyzed. We conclude that these are good starting points to estimate the partition function with AIS with a relatively low computational cost.

Related papers

• Calculating the expected value function of a two-stage stochastic optimization program with a quantum algorithm [0.0]
  Two-stage optimization involves calculating the expected cost of future decisions to inform the best decision in the present. We provide a quantum algorithm to estimate the expected value function in a two-stage optimization problem in time largely independent from the complexity of the random variable.
  arXiv  Detail & Related papers  (2024-02-23T00:07:34Z)
• Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP [81.00800920928621]
  We study representation learning in partially observable Markov Decision Processes (POMDPs) We first present an algorithm for decodable POMDPs that combines maximum likelihood estimation (MLE) and optimism in the face of uncertainty (OFU) We then show how to adapt this algorithm to also work in the broader class of $gamma$-observable POMDPs.
  arXiv  Detail & Related papers  (2023-06-21T16:04:03Z)
• Learning Unnormalized Statistical Models via Compositional Optimization [73.30514599338407]
  Noise-contrastive estimation(NCE) has been proposed by formulating the objective as the logistic loss of the real data and the artificial noise. In this paper, we study it a direct approach for optimizing the negative log-likelihood of unnormalized models.
  arXiv  Detail & Related papers  (2023-06-13T01:18:16Z)
• A Learning-Based Optimal Uncertainty Quantification Method and Its Application to Ballistic Impact Problems [1.713291434132985]
  This paper concerns the optimal (supremum and infimum) uncertainty bounds for systems where the input (or prior) measure is only partially/imperfectly known. We demonstrate the learning based framework on the uncertainty optimization problem. We show that the approach can be used to construct maps for the performance certificate and safety in engineering practice.
  arXiv  Detail & Related papers  (2022-12-28T14:30:53Z)
• Robust leave-one-out cross-validation for high-dimensional Bayesian models [0.0]
  Leave-one-out cross-validation (LOO-CV) is a popular method for estimating out-of-sample predictive accuracy. Here we propose and analyze a novel mixture estimator to compute LOO-CV criteria. Our method retains the simplicity and computational convenience of classical approaches, while guaranteeing finite variance of the resulting estimators.
  arXiv  Detail & Related papers  (2022-09-19T17:14:52Z)
• Parallel Stochastic Mirror Descent for MDPs [72.75921150912556]
  We consider the problem of learning the optimal policy for infinite-horizon Markov decision processes (MDPs) Some variant of Mirror Descent is proposed for convex programming problems with Lipschitz-continuous functionals. We analyze this algorithm in a general case and obtain an estimate of the convergence rate that does not accumulate errors during the operation of the method.
  arXiv  Detail & Related papers  (2021-02-27T19:28:39Z)
• Efficient semidefinite-programming-based inference for binary and multi-class MRFs [83.09715052229782]
  We propose an efficient method for computing the partition function or MAP estimate in a pairwise MRF. We extend semidefinite relaxations from the typical binary MRF to the full multi-class setting, and develop a compact semidefinite relaxation that can again be solved efficiently using the solver.
  arXiv  Detail & Related papers  (2020-12-04T15:36:29Z)
• Variance based sensitivity analysis for Monte Carlo and importance sampling reliability assessment with Gaussian processes [0.0]
  We propose a methodology to quantify the sensitivity of the probability of failure estimator to two uncertainty sources. This analysis also enables to control the whole error associated to the failure probability estimate and thus provides an accuracy criterion on the estimation. The approach is proposed for both a Monte Carlo based method as well as an importance sampling based method, seeking to improve the estimation of rare event probabilities.
  arXiv  Detail & Related papers  (2020-11-30T17:06:28Z)
• Efficient Evaluation of the Partition Function of RBMs with Annealed Importance Sampling [0.30458514384586394]
  Annealed Importance Sampling (AIS) method provides a tool to estimate the partition function of the system. We analyze the performance of AIS in both small- and large-sized problems, and show that in both cases a good estimation of Z can be obtained with little computational cost.
  arXiv  Detail & Related papers  (2020-07-23T10:59:04Z)
• Learning Minimax Estimators via Online Learning [55.92459567732491]
  We consider the problem of designing minimax estimators for estimating parameters of a probability distribution. We construct an algorithm for finding a mixed-case Nash equilibrium.
  arXiv  Detail & Related papers  (2020-06-19T22:49:42Z)
• Active Model Estimation in Markov Decision Processes [108.46146218973189]
  We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP) We show that our Markov-based algorithm outperforms both our original algorithm and the maximum entropy algorithm in the small sample regime.
  arXiv  Detail & Related papers  (2020-03-06T16:17:24Z)

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.