Stationary MMD Points for Cubature

• URL: http://arxiv.org/abs/2505.20754v1
• Date: Tue, 27 May 2025 05:53:19 GMT
• Title: Stationary MMD Points for Cubature
• Abstract summary: Approximation of a target probability using a finite set of points is a problem of fundamental importance.<n>We show that for integrands in the associated Hilbert space, the cubature error of stationary MMD points vanishes fastersuperconvergence than the MMD.
• Score: 14.356142724423822
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Approximation of a target probability distribution using a finite set of points is a problem of fundamental importance, arising in cubature, data compression, and optimisation. Several authors have proposed to select points by minimising a maximum mean discrepancy (MMD), but the non-convexity of this objective precludes global minimisation in general. Instead, we consider \emph{stationary} points of the MMD which, in contrast to points globally minimising the MMD, can be accurately computed. Our main theoretical contribution is the (perhaps surprising) result that, for integrands in the associated reproducing kernel Hilbert space, the cubature error of stationary MMD points vanishes \emph{faster} than the MMD. Motivated by this \emph{super-convergence} property, we consider discretised gradient flows as a practical strategy for computing stationary points of the MMD, presenting a refined convergence analysis that establishes a novel non-asymptotic finite-particle error bound, which may be of independent interest.

Related papers

• Nonparametric learning of stochastic differential equations from sparse and noisy data [2.389598109913754]
  We learn the entire drift function directly from data without strong structural assumptions.<n>We develop an Expectation-Maximization (EM) algorithm that employs a novel Sequential Monte Carlo (SMC) method.<n>The resulting EM-SMC-RKHS procedure enables accurate estimation of the drift function of dynamical systems in low-data regimes.
  arXiv  Detail & Related papers  (2025-08-15T17:01:59Z)
• Distributionally Robust Optimization via Iterative Algorithms in Continuous Probability Spaces [6.992239210938067]
  We consider a minimax problem motivated by distributionally robust optimization (DRO) when the worst-case distribution is continuous.<n>Recent research has explored learning the worst-case distribution using neural network-based generative networks.<n>This paper bridges this theoretical challenge by presenting an iterative algorithm to solve such a minimax problem.
  arXiv  Detail & Related papers  (2024-12-29T19:31:23Z)
• Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling [15.55478112106342]
  We consider the problem of approximating integrals with respect to a target probability measure using only pointwise evaluations of the integrand.<n>We propose an efficient procedure which exploits a small i.i.d. random subset of $mn$ samples drawn either uniformly or using approximate leverage scores from the initial observations.
  arXiv  Detail & Related papers  (2023-11-22T17:44:18Z)
• Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds [77.4346324549323]
  We show that a step size agnostic to the curvature of the manifold achieves a curvature-independent and linear last-iterate convergence rate. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence has not been considered before.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization [61.26619639722804]
  We propose a conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. The proposed method, equipped with an average gradient (SAG) estimator, requires only one sample per iteration. Nevertheless, it guarantees fast convergence rates on par with more sophisticated variance reduction techniques.
  arXiv  Detail & Related papers  (2022-02-26T19:10:48Z)
• Minimax Optimization: The Case of Convex-Submodular [50.03984152441271]
  Minimax problems extend beyond the continuous domain to mixed continuous-discrete domains or even fully discrete domains. We introduce the class of convex-submodular minimax problems, where the objective is convex with respect to the continuous variable and submodular with respect to the discrete variable. Our proposed algorithms are iterative and combine tools from both discrete and continuous optimization.
  arXiv  Detail & Related papers  (2021-11-01T21:06:35Z)
• Keep it Tighter -- A Story on Analytical Mean Embeddings [0.6445605125467574]
  Kernel techniques are among the most popular and flexible approaches in data science. Mean embedding gives rise to a divergence measure referred to as maximum mean discrepancy (MMD) In this paper we focus on the problem of MMD estimation when the mean embedding of one of the underlying distributions is available analytically.
  arXiv  Detail & Related papers  (2021-10-15T21:29:27Z)
• 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)
• A Note on Optimizing Distributions using Kernel Mean Embeddings [94.96262888797257]
  Kernel mean embeddings represent probability measures by their infinite-dimensional mean embeddings in a reproducing kernel Hilbert space. We show that when the kernel is characteristic, distributions with a kernel sum-of-squares density are dense. We provide algorithms to optimize such distributions in the finite-sample setting.
  arXiv  Detail & Related papers  (2021-06-18T08:33:45Z)
• Entropy Minimizing Matrix Factorization [102.26446204624885]
  Nonnegative Matrix Factorization (NMF) is a widely-used data analysis technique, and has yielded impressive results in many real-world tasks. In this study, an Entropy Minimizing Matrix Factorization framework (EMMF) is developed to tackle the above problem. Considering that the outliers are usually much less than the normal samples, a new entropy loss function is established for matrix factorization.
  arXiv  Detail & Related papers  (2021-03-24T21:08:43Z)
• Performance analysis of greedy algorithms for minimising a Maximum Mean Discrepancy [0.0]
  We show that the finite-sample-size approximation error, measured by the MMD, decreases as $1/n$ for SBQ. The upper bound on the approximation error is slightly better for SBQ, but the other methods are significantly faster.
  arXiv  Detail & Related papers  (2021-01-19T11:18:51Z)
• Log-Likelihood Ratio Minimizing Flows: Towards Robust and Quantifiable Neural Distribution Alignment [52.02794488304448]
  We propose a new distribution alignment method based on a log-likelihood ratio statistic and normalizing flows. We experimentally verify that minimizing the resulting objective results in domain alignment that preserves the local structure of input domains.
  arXiv  Detail & Related papers  (2020-03-26T22:10:04Z)
• Consensus-Based Optimization on the Sphere: Convergence to Global Minimizers and Machine Learning [7.998311072988401]
  We investigate the implementation of a new Kuramoto-Vicsek-type model for global optimization of non functions on the sphere. We present several numerical experiments, which show that the algorithm proposed in the present paper scales well with the dimension and is extremely versatile.
  arXiv  Detail & Related papers  (2020-01-31T18:23:26Z)

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.