Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian
Monte Carlo
- URL: http://arxiv.org/abs/2107.07211v1
- Date: Thu, 15 Jul 2021 09:39:14 GMT
- Title: Decentralized Bayesian Learning with Metropolis-Adjusted Hamiltonian
Monte Carlo
- Authors: Vyacheslav Kungurtsev and Adam Cobb and Tara Javidi and Brian Jalaian
- Abstract summary: We show that Langevin Hamiltonian methods are effective at realizing a gradient of a random quantity.
We present the first approach to incorporating constant step-size methods with a Metropolis- HMC.
- Score: 15.20294178835262
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Federated learning performed by a decentralized networks of agents is
becoming increasingly important with the prevalence of embedded software on
autonomous devices. Bayesian approaches to learning benefit from offering more
information as to the uncertainty of a random quantity, and Langevin and
Hamiltonian methods are effective at realizing sampling from an uncertain
distribution with large parameter dimensions. Such methods have only recently
appeared in the decentralized setting, and either exclusively use stochastic
gradient Langevin and Hamiltonian Monte Carlo approaches that require a
diminishing stepsize to asymptotically sample from the posterior and are known
in practice to characterize uncertainty less faithfully than constant step-size
methods with a Metropolis adjustment, or assume strong convexity properties of
the potential function. We present the first approach to incorporating constant
stepsize Metropolis-adjusted HMC in the decentralized sampling framework, show
theoretical guarantees for consensus and probability distance to the posterior
stationary distribution, and demonstrate their effectiveness numerically on
standard real world problems, including decentralized learning of neural
networks which is known to be highly non-convex.
Related papers
- On Measuring Calibration of Discrete Probabilistic Neural Networks [3.120856767382004]
Training neural networks to fit high-dimensional probability distributions via maximum likelihood has become an effective method for uncertainty quantification.
Traditional metrics like Expected Error (ECE) and Negative Log Likelihood (NLL) have limitations.
This paper proposes a new approach using conditional kernel mean embeddings to measure calibration discrepancies without these biases and assumptions.
arXiv Detail & Related papers (2024-05-20T23:30:07Z) - A Compact Representation for Bayesian Neural Networks By Removing
Permutation Symmetry [22.229664343428055]
We show that the role of permutations can be meaningfully quantified by a number of transpositions metric.
We then show that the recently proposed rebasin method allows us to summarize HMC samples into a compact representation.
We show that this compact representation allows us to compare trained BNNs directly in weight space across sampling methods and variational inference.
arXiv Detail & Related papers (2023-12-31T23:57:05Z) - Statistical guarantees for stochastic Metropolis-Hastings [0.0]
By calculating acceptance probabilities on batches, a Metropolis-Hastings step saves computational costs, but reduces the effective sample size.
We show that this obstacle can be avoided by a simple correction term.
We show that the Metropolis-Hastings algorithm indeed behave similar to those obtained from the classical Metropolis-adjusted Langevin algorithm.
arXiv Detail & Related papers (2023-10-13T18:00:26Z) - Bayesian deep learning framework for uncertainty quantification in high
dimensions [6.282068591820945]
We develop a novel deep learning method for uncertainty quantification in partial differential equations based on Bayesian neural network (BNN) and Hamiltonian Monte Carlo (HMC)
A BNN efficiently learns the posterior distribution of the parameters in deep neural networks by performing Bayesian inference on the network parameters.
The posterior distribution is efficiently sampled using HMC to quantify uncertainties in the system.
arXiv Detail & Related papers (2022-10-21T05:20:06Z) - NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural
Networks [151.03112356092575]
We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution.
We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
arXiv Detail & Related papers (2022-02-07T12:30:45Z) - Sampling asymmetric open quantum systems for artificial neural networks [77.34726150561087]
We present a hybrid sampling strategy which takes asymmetric properties explicitly into account, achieving fast convergence times and high scalability for asymmetric open systems.
We highlight the universal applicability of artificial neural networks, underlining the universal applicability of neural networks.
arXiv Detail & Related papers (2020-12-20T18:25:29Z) - Amortized Conditional Normalized Maximum Likelihood: Reliable Out of
Distribution Uncertainty Estimation [99.92568326314667]
We propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation.
Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle.
We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration on out-of-distribution inputs.
arXiv Detail & Related papers (2020-11-05T08:04:34Z) - Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian
Monte Carlo [8.94392435424862]
Decentralized SGLD (DE-SGLD) and Decentralized SGHMC (DE-SGHMC) are algorithms for scaleable Bayesian inference in the decentralized setting for large datasets.
We show that when the posterior distribution is strongly log-concave and smooth, the iterates of these algorithms converge linearly to a neighborhood of the target distribution in the 2-Wasserstein distance.
arXiv Detail & Related papers (2020-07-01T16:26:00Z) - Unlabelled Data Improves Bayesian Uncertainty Calibration under
Covariate Shift [100.52588638477862]
We develop an approximate Bayesian inference scheme based on posterior regularisation.
We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
arXiv Detail & Related papers (2020-06-26T13:50:19Z) - A Distributional Analysis of Sampling-Based Reinforcement Learning
Algorithms [67.67377846416106]
We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes.
We show that value-based methods such as TD($lambda$) and $Q$-Learning have update rules which are contractive in the space of distributions of functions.
arXiv Detail & Related papers (2020-03-27T05:13:29Z) - Decentralized MCTS via Learned Teammate Models [89.24858306636816]
We present a trainable online decentralized planning algorithm based on decentralized Monte Carlo Tree Search.
We show that deep learning and convolutional neural networks can be employed to produce accurate policy approximators.
arXiv Detail & Related papers (2020-03-19T13:10:20Z)
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.