English
Related papers

Related papers: Bures-Wasserstein Importance-Weighted Evidence Low…

200 papers

Optimization over the space of probability measures endowed with the Wasserstein-2 geometry is central to modern machine learning and mean-field modeling. However, traditional methods relying on full Wasserstein gradients often suffer from…

Machine Learning · Statistics 2026-04-03 Yewei Xu , Qin Li

Bayesian optimal experimental design (BOED) seeks to maximize the expected information gain (EIG) of experiments. This requires a likelihood estimate, which in many settings is intractable. Simulation-based inference (SBI) provides powerful…

Machine Learning · Computer Science 2026-02-09 Samuel Klein , Willie Neiswanger , Daniel Ratner , Michael Kagan , Sean Gasiorowski

We investigate the use of alternative divergences to Kullback-Leibler (KL) in variational inference(VI), based on the Variational Dropout \cite{kingma2015}. Stochastic gradient variational Bayes (SGVB) \cite{aevb} is a general framework for…

Machine Learning · Statistics 2017-11-15 Bogdan Mazoure , Riashat Islam

Optimizing parameterized quantum circuits is a key routine in using near-term quantum devices. However, the existing algorithms for such optimization require an excessive number of quantum-measurement shots for estimating expectation values…

Quantum Physics · Physics 2022-08-04 Shiro Tamiya , Hayata Yamasaki

Inverse probability weighting (IPW) is widely used in many areas when data are subject to unrepresentativeness, missingness, or selection bias. An inevitable challenge with the use of IPW is that the IPW estimator can be remarkably unstable…

Methodology · Statistics 2021-11-29 Yukun Liu , Yan Fan

As opposed to standard empirical risk minimization (ERM), distributionally robust optimization aims to minimize the worst-case risk over a larger ambiguity set containing the original empirical distribution of the training data. In this…

Machine Learning · Computer Science 2021-01-06 Jaeho Lee , Maxim Raginsky

Variational Inference approximates an unnormalized distribution via the minimization of Kullback-Leibler (KL) divergence. Although this divergence is efficient for computation and has been widely used in applications, it suffers from some…

Machine Learning · Statistics 2022-07-28 Mingxuan Yi , Song Liu

Gaussian mixture models (GMM) are powerful parametric tools with many applications in machine learning and computer vision. Expectation maximization (EM) is the most popular algorithm for estimating the GMM parameters. However, EM…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Soheil Kolouri , Gustavo K. Rohde , Heiko Hoffmann

We propose a modification of the standard linear implicit Euler integrator for the weak approximation of parabolic semilinear stochastic PDEs driven by additive space-time white noise. The new method can easily be combined with a finite…

Numerical Analysis · Mathematics 2022-03-22 Charles-Edouard Bréhier

We introduce and study a novel model-selection strategy for Bayesian learning, based on optimal transport, along with its associated predictive posterior law: the Wasserstein population barycenter of the posterior law over models. We first…

Machine Learning · Statistics 2022-11-10 Julio Backhoff-Veraguas , Joaquin Fontbona , Gonzalo Rios , Felipe Tobar

In the theory of second-order, nonlinear elliptic and parabolic equations, obtaining local or global gradient bounds is often a key step for proving the existence of solutions but it may be even more useful in many applications, for example…

Analysis of PDEs · Mathematics 2021-08-30 G Barles

The Wasserstein distance quantifies the distance between two probability measures on a metric space. We prove an analogue of the Berry-Esseen inequality for the Wasserstein distance on a finite area hyperbolic surface. This inequality…

Number Theory · Mathematics 2025-12-18 Peter Humphries

Wasserstein barycenters provide a principled approach for aggregating probability measures, while preserving the geometry of their ambient space. Existing discrete methods are not scalable as they assume access to the complete set of…

Machine Learning · Statistics 2026-03-10 Eduardo Fernandes Montesuma , Yassir Bendou , Mike Gartrell

Gradient bounds had proved to be a very efficient tool for the control of the rate of convergence to equilibrium for parabolic evolution equations. Among the gradient bounds methods, the celebrated Bakry-\'Emery criterion is a powerful way…

Analysis of PDEs · Mathematics 2016-02-25 Fabrice Baudoin

Tightness remains the center quest in all modern estimation bounds. For very weak signals, this is made possible with judicial choices of prior probability distribution and bound family. While current bounds in GNSS assess performance of…

Signal Processing · Electrical Eng. & Systems 2024-01-12 Xin Zhang , Xingqun Zhan , Jihong Huang , Jiahui Liu , Yingchao Xiao

We study a general formulation of regularized Wasserstein barycenters that enjoys favorable regularity, approximation, stability and (grid-free) optimization properties. This barycenter is defined as the unique probability measure that…

Optimization and Control · Mathematics 2025-07-28 Lénaïc Chizat

Consider a set of points sampled independently near a smooth compact submanifold of Euclidean space. We provide mathematically rigorous bounds on the number of sample points required to estimate both the dimension and the tangent spaces of…

Statistics Theory · Mathematics 2023-09-26 Uzu Lim , Harald Oberhauser , Vidit Nanda

Variational inference (VI) is a method to approximate the computationally intractable posterior distributions that arise in Bayesian statistics. Typically, VI fits a simple parametric distribution to the target posterior by minimizing an…

Machine Learning · Statistics 2023-07-18 Chirag Modi , Charles Margossian , Yuling Yao , Robert Gower , David Blei , Lawrence Saul

Inference in discrete graphical models with variational methods is difficult because of the inability to re-parameterize gradients of the Evidence Lower Bound (ELBO). Many sampling-based methods have been proposed for estimating these…

Machine Learning · Computer Science 2020-10-23 Andy Shih , Stefano Ermon

We introduce a stochastic variational inference procedure for training scalable Gaussian process (GP) models whose per-iteration complexity is independent of both the number of training points, $n$, and the number basis functions used in…

Machine Learning · Statistics 2020-06-05 Trefor W. Evans , Prasanth B. Nair