This paper optimizes functions of probability measures using particle gradient descent for displacement convex functions.
problem Optimizing functions of probability measures with displacement convex properties.
method Particle gradient descent applied to displacement convex functions with theoretical guarantees.
result Finite number of particles and computations are sufficient to find optimal solutions for displacement convex functions.
A new stochastic algorithm approximates optimal distributions without requiring propagation of chaos.
problem Optimizing functionals over probability distributions using finite particle systems.
method Virtual particle stochastic approximation, viewed as a form of stochastic gradient descent in the Wasserstein space.
result The algorithm's output converges to the optimal distribution and produces i.i.d. samples.
SVGD algorithm converges at rate 1/sqrt(log log n) for sub-Gaussian distributions.
problem Approximating a probability distribution with particles.
method Stein variational gradient descent (SVGD) with finite particles and sub-Gaussian target distribution.
result SVGD achieves a convergence rate of 1/sqrt(log log n) for sub-Gaussian distributions.
USD algorithm transports distributions with or without mass conservation.
problem Transporting distributions with different masses.
method Particle descent algorithm using Sobolev-Fisher discrepancy.
result USD converges to target distribution in MMD sense.
The paper analyzes rates for a modified gradient descent method using Stein variational gradients.
problem Improving the accuracy of gradient descent methods for complex target distributions.
method Derives finite-particle rates for regularized Stein variational gradient descent (R-SVGD).
result Establishes explicit non-asymptotic bounds for time-averaged empirical measures.
Improves SVGD for high-dimensional Bayesian inference by reducing variance collapse.
problem Variance collapse in SVGD reduces accuracy and diversity of estimation.
method Augmented Message Passing SVGD (AUMP-SVGD) method, a two-stage optimization procedure.
result AUMP-SVGD achieves satisfactory accuracy and overcomes variance collapse in various benchmark problems.
KSD Descent uses KSD to sample from a target distribution efficiently.
problem Sampling from complex target distributions efficiently.
method Wasserstein gradient flow of KSD, using L-BFGS optimization.
result KSD Descent can sample from a target distribution using a set of particles.
MWGraD solves multi-objective distributional optimization using particle-based gradient descent.
problem Simultaneously minimize multiple objective functionals over probability distributions.
method Iterative particle-based algorithm MWGraD, estimating and aggregating Wasserstein gradients.
result Demonstrates effectiveness on synthetic and real-world datasets.
Improved convergence rates for Stein Variational Gradient Descent in finite-particle settings.
problem Improving convergence rates for Stein Variational Gradient Descent in finite-particle settings.
method Analyzing the time derivative of relative entropy and splitting it into dominant and smaller parts.
result Finite-particle convergence rates of order 1/\sqrt{N} for Kernelized Stein Discrepancy and Wasserstein-2 metrics.
New particle algorithms optimize latent variable models.
problem Optimizing latent variable models for maximum likelihood estimation.
method Identify gradient flows associated with free energy functional and discretize them to create particle-based algorithms.
result Novel particle algorithms scale to high-dimensional settings and perform well in experiments.
Bayesian methods are appealing in their flexibility in modeling complex data and ability in capturing uncertainty in parameters. However, when Bayes' rule does not result in tractable closed-form, most approximate inference algorithms lack either scalability or rigorous guarantees. To tackle this challenge, we propose …
We study an interacting particle system in R d \mathbf{R}^d R d motivated by Stein variational gradient descent [Q. Liu and D. Wang, NIPS 2016], a deterministic algorithm for sampling from a given probability density with unknown normalization. We prove that in the large particle limit the empirical measure of the particle s…
FS&P uses birth-death process to ensure global convergence of stochastic conic particle gradient descent.
problem Global optimization of non-convex objective functions over measure space.
method Introduces Fast Spawn\&Prune (FS\&P) combining CPGD with birth-death process.
result First theoretical guarantee of global convergence for discrete-time stochastic algorithms.
Online convex optimization is a sequential prediction framework with the goal to track and adapt to the environment through evaluating proper convex loss functions. We study efficient particle filtering methods from the perspective of such a framework. We formulate an efficient particle filtering methods for the non-st…
Paper explores SVGD for Bayesian inference, linking deterministic and stochastic dynamics.
problem Bayesian inference and Markov chain Monte Carlo methods.
method Stein variational gradient descent (SVGD) with deterministic and stochastic dynamics.
result Identifies Stein-Fisher information as the leading order contribution in the long-time and many-particle regime.
BSVGD improves sampling for multimodal distributions using branching.
problem Sampling from multimodal distributions.
method Random branching in Stein Variational Gradient Descent (SVGD).
result Theoretical convergence guarantee and empirical validation.
New particle-based VI algorithm expands function class and improves scalability.
problem Limited function class in particle-based VI algorithms restricts flexibility and scalability.
method Introduces a functional regularization term to expand the function class and proposes PFG algorithm.
result Proposed PFG algorithm has larger function class, improved scalability, better adaptation to ill-conditioned distributions, and provable convergence.
Differentiable resampling improves particle filter performance.
problem Non-differentiability of traditional resampling in particle filters.
method Introduced a neural network resampler (particle transformer) trained with a likelihood-based loss function.
result Learned resampling outperforms traditional methods on synthetic and real-world tasks.
DSVGD improves federated learning with fewer communication rounds.
problem Federated learning scalability and trustworthiness.
method Distributed Stein Variational Gradient Descent (DSVGD) for non-parametric Bayesian inference.
result DSVGD achieves comparable accuracy and scalability to other methods, with well-calibrated predictions.
Stein variational gradient descent (SVGD) is a recently proposed particle-based Bayesian inference method, which has attracted a lot of interest due to its remarkable approximation ability and particle efficiency compared to traditional variational inference and Markov Chain Monte Carlo methods. However, we observed th…
A new model for generating point processes with complex geometries.
problem Difficulties in modeling point processes with large numbers of particles and complex geometries.
method Gradient descent algorithm applied to a phase harmonic operator on wavelet transforms of point patterns.
result The model allows for fast sampling of new configurations that match the statistics of observed point processes.
A new ParVI framework improves particle-based variational inference methods.
problem Non-trivial kernel design in particle-based variational inference methods.
method Proposes a generalized Wasserstein gradient descent (GWG) framework with broader regularizers.
result Demonstrates strong convergence guarantees and effectiveness on simulated and real data.
Gaussian-SVGD dynamics converge to Gaussian distributions under certain conditions.
problem Understanding the theoretical properties of SVGD, especially for Gaussian targets.
method Detailed theoretical study of Gaussian-SVGD dynamics, considering both mean-field PDE and discrete particle systems.
result Gaussian-SVGD dynamics converge linearly to the Gaussian distribution closest to the target in KL divergence.
We propose in this work RBM-SVGD, a stochastic version of Stein Variational Gradient Descent (SVGD) method for efficiently sampling from a given probability measure and thus useful for Bayesian inference. The method is to apply the Random Batch Method (RBM) for interacting particle systems proposed by Jin et al to the …
Paper analyzes SVGD algorithm for non-asymptotic convergence.
problem Optimizing a set of particles to approximate a target probability distribution.
method Finite time analysis of SVGD algorithm, providing descent lemma and convergence rates.
result SVGD algorithm decreases the objective at each iteration and converges to the target distribution.
A new algorithm solves sparse optimization problems on measures efficiently.
problem Sparse optimization problems on measures.
method Over-parameterized Stochastic Gradient Descent with Random Features.
result Global convergence with rate O ( log ( K ) / K ) O(\log(K)/\sqrt{K}) O ( log ( K ) / K ) and bounded total variation norms. Paper proposes LSVGD to stabilize GAN training via Langevin Stein Variational Gradient Descent.
problem Mode collapse and performance deterioration in GAN training.
method Langevin Stein Variational Gradient Descent (LSVGD) incorporating noise to stabilize training.
result LSVGD improves performance and stability of various GAN models.
Two SVGD variants achieve fast convergence with provable guarantees.
problem Understanding and improving SVGD's performance with finite particles.
method Introducing virtual particles and novel stochastic approximations.
result Provable fast convergence rates for finite-particle SVGD variants.
A new method de-randomizes MCMC dynamics using the Stein operator.
problem Estimating complex target distributions in Bayesian inference.
method De-randomized kernel-based particle samplers that discretize the fiber-gradient Hamiltonian flow.
result GSVGD de-randomizes complex MCMC dynamics, maintaining high sample quality.
A new algorithm learns model regimes and parameters efficiently.
problem Learning high-dimensional parameters with discontinuous jumps.
method Differentiable interacting multiple model particle filter with gradient descent.
result Superior numerical performance compared to previous methods.
Particle-based variational inference offers a flexible way of approximating complex posterior distributions with a set of particles. In this paper we introduce a new particle-based variational inference method based on the theory of semi-discrete optimal transport. Instead of minimizing the KL divergence between the po…
Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study a simple minimization method: the unknown measure is discretized into a mixture…
Particle-optimization-based sampling (POS) is a recently developed effective sampling technique that interactively updates a set of particles. A representative algorithm is the Stein variational gradient descent (SVGD). We prove, under certain conditions, SVGD experiences a theoretical pitfall, {\it i.e.}, particles te…
SBS uses SVGD to optimize continuous functions globally.
problem Global optimization of continuous Sobolev functions.
method Stein Boltzmann Sampling (SBS) with SVGD.
result SBS and its variants are highly competitive in global optimization.
Improved particle approximation for mean-field neural networks.
problem Particle approximation error for mean-field neural networks.
method Improved particle approximation error by leveraging the problem structure in risk minimization.
result Established an LSI-constant-free particle approximation error concerning the objective gap.
MT-SGD samples from multiple target distributions using gradient descent.
problem Sampling from multiple unnormalized target distributions.
method Proposes MT-SGD, a flow of intermediate distributions to sample from multiple target distributions.
result Asymptotic analysis shows MT-SGD reduces to multiple-gradient descent for multi-objective optimization.
This work finds mixed equilibria in machine learning problems using measures and simultaneous gradient ascent-descent.
problem Finding pure equilibria in machine learning problems is computationally hard.
method Entropic regularization, simultaneous gradient ascent-descent, and particle discretization in the Wasserstein metric.
result Global convergence towards the global equilibrium in mixed equilibria problems.
New samplers minimize KL divergence for constrained and non-Euclidean geometries.
problem Efficient sampling from constrained and non-Euclidean distributions.
method Stein Variational Mirror Descent and Mirrored Stein Variational Gradient Descent.
result New samplers converge more rapidly and accurately than prior methods.
New algorithm for fitting Gaussian mixtures using Wasserstein-Fisher-Rao geometry.
problem Hard problem of fitting Gaussian mixture models to data computationally.
method Gradient descent over Wasserstein-Fisher-Rao geometry for probability measures.
result Established convergence guarantees for the proposed algorithm.
SMI uses mixture models to improve SVGD's performance in Bayesian inference.
problem Variance collapse in SVGD for Bayesian inference, especially with small models.
method Generalizes SVGD to Stein mixture models, optimizing an ELBO lower bound.
result SMI avoids variance collapse and accurately estimates uncertainty for small BNNs.
ASVGD accelerates SVGD for efficient sampling.
problem Slow SVGD in high-dimensional sampling.
method Accelerated gradient flow in a metric space of probability densities, using Nesterov's method and momentum-based updates.
result ASVGD outperforms SVGD and other methods in sampling efficiency.
CBO interprets as SGD, leading to global convergence for nonconvex functions.
problem Understanding and improving gradient-based learning algorithms.
method Interpreting CBO as a stochastic relaxation of SGD.
result CBO provably converges globally to minimizers for nonsmooth nonconvex functions.
A new EVI framework improves ParVI methods by maintaining variational structure and reducing KL-divergence.
problem Improving variational inference methods for better approximation of target distributions.
method EVI framework that minimizes the VI objective function based on an energy-dissipation law, including a new 'Approximation-then-Variation' scheme.
result The new scheme significantly decreases KL-divergence and outperforms existing ParVI methods in fidelity.
New method improves convergence and reduces variance in noisy optimization problems.
problem Computing exact minimizers with noisy gradient information.
method Stochastic mirror descent with interacting particles.
result Interaction helps improve convergence and reduce variance.
Method identifies mixed Nash equilibria in high dimensions for training mixtures of GANs.
problem Finding Nash equilibria in two-player zero-sum continuous games, especially in high dimensions.
method Parametrizing mixed strategies as mixtures of particles, updating their positions and weights using gradient descent-ascent.
result Global convergence to an approximate equilibrium for the related Langevin gradient-ascent dynamic.
Proves error bounds for PGD, extending log-Sobolev and Talagrand inequalities.
problem Maximum likelihood estimation of large latent variable models.
method Extending log-Sobolev and Talagrand inequalities to models with strongly concave log-likelihoods.
result Non-asymptotic error bounds for PGD in models satisfying LSI and PŁI.
Stochastic particle-optimization sampling (SPOS) is a recently-developed scalable Bayesian sampling framework that unifies stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD) algorithms based on Wasserstein gradient flows. With a rigorous non-asymptotic convergence theory developed recently…
Generative method avoids function estimation for data generation.
problem Challenges in function estimation for generative models.
method Deterministic point transport with gradient descent.
result Data generation possible without function estimation.