• Corpus ID: 54438205

Stochastic Gradient MCMC with Repulsive Forces

@article{Gallego2018StochasticGM,
  title={Stochastic Gradient MCMC with Repulsive Forces},
  author={V{\'i}ctor Gallego and David R{\'i}os Insua},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.00071}
}
We propose a unifying view of two different families of Bayesian inference algorithms, SG-MCMC and SVGD. We show that SVGD plus a noise term can be framed as a multiple chain SG-MCMC method. Instead of treating each parallel chain independently from others, the proposed algorithm implements a repulsive force between particles, avoiding collapse. Experiments in both synthetic distributions and real datasets show the benefits of the proposed scheme. 

Figures and Tables from this paper

Stein Self-Repulsive Dynamics: Benefits From Past Samples

We propose a new Stein self-repulsive dynamics for obtaining diversified samples from intractable un-normalized distributions. Our idea is to introduce Stein variational gradient as a repulsive force

A stochastic Stein Variational Newton method

TLDR
This paper derives, and provides a practical implementation of, a stochastic variant of SVN (sSVN) which is both asymptotically correct and converges rapidly and is a promising approach to accelerating high-precision Bayesian inference tasks with modest-dimension.

Understanding MCMC Dynamics as Flows on the Wasserstein Space

TLDR
A theoretical framework is proposed that recognizes a general MCMC dynamics as the fiber-gradient Hamiltonian flow on the Wasserstein space of a fiber-Riemannian Poisson manifold and enables ParVI simulation of MCMC Dynamics, which enriches the ParVI family with more efficient dynamics, and also adapts ParVI advantages to MCMCs.

A STOCHASTIC S TEIN VARIATIONAL N EWTON METHOD

TLDR
This paper derives, and provides a practical implementation of, a stochastic variant of SVN (sSVN) which is both asymptotically correct and converges rapidly and is a promising approach to accelerating high-precision Bayesian inference tasks with modest-dimension.

Variationally Inferred Sampling through a Refined Bound

TLDR
A framework to boost the efficiency of Bayesian inference in probabilistic models is introduced by embedding a Markov chain sampler within a variational posterior approximation, called “refined variational approximation”.

Stein Variational Gradient Descent: many-particle and long-time asymptotics

TLDR
This paper considers the originally proposed deterministic dynamics as well as a stochastic variant, each of which represent one of the two main paradigms in Bayesian computational statistics: variational inference and Markov chain Monte Carlo.

On Stein Variational Neural Network Ensembles

TLDR
It is found that SVGD using functional and hybrid kernels can overcome the limitations of deep ensembles and improves on functional diversity and uncertainty estimation and approaches the true Bayesian posterior more closely.

Neural Variational Gradient Descent

TLDR
This work proposes Neural Variational Gradient Descent (NVGD), which is based on parametrizing the witness function of the Stein discrepancy by a deep neural network whose parameters are learned in parallel to the inference, mitigating the necessity to make any kernel choices whatsoever.

On the geometry of Stein variational gradient descent

TLDR
This paper focuses on the recently introduced Stein variational gradient descent methodology, a class of algorithms that rely on iterated steepest descent steps with respect to a reproducing kernel Hilbert space norm, and considers certain nondifferentiable kernels with adjusted tails.

Feature Space Particle Inference for Neural Network Ensembles

TLDR
This study proposes optimizing particles in the feature space where the activation of a specific intermediate layer lies to address the above-mentioned difflculties, and encourages each member to capture distinct features, which is expected to improve ensemble prediction robustness.

References

SHOWING 1-7 OF 7 REFERENCES

Bayesian Learning via Stochastic Gradient Langevin Dynamics

In this paper we propose a new framework for learning from large scale datasets based on iterative learning from small mini-batches. By adding the right amount of noise to a standard stochastic

Stochastic Gradient Hamiltonian Monte Carlo

TLDR
A variant that uses second-order Langevin dynamics with a friction term that counteracts the effects of the noisy gradient, maintaining the desired target distribution as the invariant distribution is introduced.

Bayesian Sampling Using Stochastic Gradient Thermostats

TLDR
This work shows that one can leverage a small number of additional variables to stabilize momentum fluctuations induced by the unknown noise inynamics-based sampling methods.

A Complete Recipe for Stochastic Gradient MCMC

TLDR
This paper provides a general recipe for constructing MCMC samplers--including stochastic gradient versions--based on continuous Markov processes specified via two matrices, and uses the recipe to straightforwardly propose a new state-adaptive sampler: stochastics gradient Riemann Hamiltonian Monte Carlo (SGRHMC).

Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm

We propose a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization. Our method iteratively transports a set of particles to match the

Variational Inference: A Review for Statisticians

TLDR
Variational inference (VI), a method from machine learning that approximates probability densities through optimization, is reviewed and a variant that uses stochastic optimization to scale up to massive data is derived.

Stein Variational Gradient Descent as Gradient Flow

TLDR
This paper develops the first theoretical analysis on SVGD, discussing its weak convergence properties and showing that its asymptotic behavior is captured by a gradient flow of the KL divergence functional under a new metric structure induced by Stein operator.