Stability of Finite-Batch Particle Mean-Field Variational Inference Beyond Strong Convexity

• URL: http://arxiv.org/abs/2608.11486v1
• Date: Tue, 11 Aug 2026 22:56:36 GMT
• Title: Stability of Finite-Batch Particle Mean-Field Variational Inference Beyond Strong Convexity
• Abstract summary: We study the implementable finitebatch particle algorithm for mean-field variational inference as a fully discrete approximation of the projected Wasserstein dynamics.<n>We prove a nonasymotic Wasserstein stability bound that separates product, contraction, finitebatch error time drifttization, and the defects accumulated along the coupled particle trajectories.
• Score: 3.0678195074387706
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the implementable finite-batch particle algorithm for mean-field variational inference as a fully discrete stochastic approximation of the projected Wasserstein dynamics. The target potential is globally smooth but need not be strongly convex. The departure from contractivity is quantified by the curvature defect \[ \mathfrak d_α(x,y) = \bigl[α\|x-y\|^2- \langle\nabla V(x)-\nabla V(y),x-y\rangle\bigr]_+, \] which is the additive loss in the one-step Euler contraction estimate. We prove a non-asymptotic Wasserstein stability bound that separates initialization, product-empirical approximation, finite-batch drift error, time discretization, and the defects accumulated along the coupled trajectories. Under the uniform bound $\mathfrak d_α\leqβ$, the particle iterates remain within $O(\sqrt{β/α})$ of any MFVI minimizer, up to explicit errors in the particle number, batch size, and step size. The proof uses a stationary comparison array whose population law is an MFVI minimizer but whose particle-level law is a random product empirical measure, and it controls the resulting projected-drift discrepancy explicitly. We also give coordinatewise defect estimates and structural conditions for dimension-independent projected-drift sensitivity, construct an arbitrary-dimensional smooth nonconvex benchmark with a closed-form MFVI minimizer, and explain why polynomially growing drifts require a modification of the untamed explicit scheme.

Related papers

• A proximal subgradient method for nonconvex stochastic optimization under the Kurdyka-Łojasiewicz condition [39.146761527401424]
  This work introduces a proximal subgradient method for minimizing the sum of an expected cost.<n>We use the Kurdyka-Lojasiewicz (KL) property to guarantee convergence of the whole trajectory to a single stationary point.
  arXiv  Detail & Related papers  (2026-08-05T23:07:27Z)
• Exact Closed-Form Quantum Correlations of Maximally Entangled Qudit States under Arbitrary Non-Markovian Pure Dephasing [0.0]
  We study the time evolution of entanglement and quantum discord for a pair of maximally entangled qudits of arbitrary dimension $d$ under non-Markovian pure dephasing.<n>Because this solution requires no Born--Markov, Lindblad, or rotating-wave approximation, every result reported here follows directly from the exact dynamics.
  arXiv  Detail & Related papers  (2026-07-22T03:05:59Z)
• Non-Asymptotic Variational Learning for Monotone Nonlinear Multiscale Elliptic Equations: Scale-Robust Primal-Dual Bounds and Strong-Form Statistical Ill-Conditioning [0.0]
  We develop a non-asymptotic approximation, sampling, and finite-iteration optimization theory for variational physics-informed approximations of uniformly nonlinear multiscale elliptic equations.<n>For boundary-compatible neural feature classes, the population error splits into approximation, empirical quadreration, and projected-gradient terms, with all non-approximation constants uniform in the microscopic scale (varepsilon)
  arXiv  Detail & Related papers  (2026-07-17T07:26:29Z)
• Anisotropic Template Ansätze for Robust Positive Invariance under State-Dependent Uncertainty [1.2234742322758416]
  We map a fixed ellipsoidal template through a GP-derived positive-definite matrix field.<n>The resulting LMI conditions couple the learned field to Schur-stable dynamics.<n> Quadrotor simulations show a $195times$ reduction in 3D velocity-tube volume.
  arXiv  Detail & Related papers  (2026-06-14T23:52:29Z)
• Is Spurious Correlation Removal Always Learnable? [56.28155520961125]
  Invariant learning can fail even when the structure is statistically identifiable.<n>We show a conditional computational barrier: under a black-box samplable supervised sparse recovery primitive, there exist emphamplable multi-dimensional environments.<n>Synthetic and real datasets illustrate the predicted gaps and transitions and motivate simple diversity diagnostics.
  arXiv  Detail & Related papers  (2026-06-11T05:49:43Z)
• Detectability Limits for Intra-Block Temporal Drift in Finite-Key Entanglement-Based QKD [0.0]
  We study the statistical detectability of intra-block temporal drift in finite-key entanglement-based quantum key distribution.<n>Dread is modeled as a mean-preserving Lipschitz perturbation of Bernoulli observables, capturing structured temporal variation.<n>The result quantifies a finite-block monitoring-resolution limit and is distinct from composable security certification.
  arXiv  Detail & Related papers  (2026-05-22T21:18:46Z)
• Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching [60.37045080890305]
  We provide the first analysis of the sample complexity for flow-matching based generative models.<n>We decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field.
  arXiv  Detail & Related papers  (2025-12-01T05:14:25Z)
• Randomized Physics-Informed Machine Learning for Uncertainty Quantification in High-Dimensional Inverse Problems [49.1574468325115]
  We propose a physics-informed machine learning method for uncertainty quantification in high-dimensional inverse problems. We show analytically and through comparison with Hamiltonian Monte Carlo that the rPICKLE posterior converges to the true posterior given by the Bayes rule.
  arXiv  Detail & Related papers  (2023-12-11T07:33:16Z)
• Noise-Free Sampling Algorithms via Regularized Wasserstein Proximals [3.4240632942024685]
  We consider the problem of sampling from a distribution governed by a potential function. This work proposes an explicit score based MCMC method that is deterministic, resulting in a deterministic evolution for particles.
  arXiv  Detail & Related papers  (2023-08-28T23:51:33Z)
• Stochastic Inexact Augmented Lagrangian Method for Nonconvex Expectation Constrained Optimization [88.0031283949404]
  Many real-world problems have complicated non functional constraints and use a large number of data points. Our proposed method outperforms an existing method with the previously best-known result.
  arXiv  Detail & Related papers  (2022-12-19T14:48:54Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)
• Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization [106.70006655990176]
  A distributional optimization problem arises widely in machine learning and statistics. We propose a novel particle-based algorithm, dubbed as variational transport, which approximately performs Wasserstein gradient descent. We prove that when the objective function satisfies a functional version of the Polyak-Lojasiewicz (PL) (Polyak, 1963) and smoothness conditions, variational transport converges linearly.
  arXiv  Detail & Related papers  (2020-12-21T18:33:13Z)

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.