English
Related papers

Related papers: Pathwise Derivatives Beyond the Reparameterization…

200 papers

In this paper, we introduce and develop the theory of semimartingale optimal transport in a path dependent setting. Instead of the classical constraints on marginal distributions, we consider a general framework of path dependent…

Probability · Mathematics 2020-09-15 Ivan Guo , Gregoire Loeper

We present a novel framework based on optimal transport for the challenging problem of comparing graphs. Specifically, we exploit the probabilistic distribution of smooth graph signals defined with respect to the graph topology. This allows…

Machine Learning · Computer Science 2019-12-09 Hermina Petric Maretic , Mireille EL Gheche , Giovanni Chierchia , Pascal Frossard

We introduce a family of pairwise stochastic gradient estimators for gradients of expectations, which are related to the log-derivative trick, but involve pairwise interactions between samples. The simplest example of our new estimator,…

Machine Learning · Computer Science 2022-04-21 Christian J. Walder , Paul Roussel , Richard Nock , Cheng Soon Ong , Masashi Sugiyama

Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used to estimate gradients of expectations throughout machine learning and reinforcement learning; however, they are usually explained as simple mathematical tricks,…

Machine Learning · Computer Science 2021-06-01 Paavo Parmas , Masashi Sugiyama

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…

Machine Learning · Statistics 2019-05-16 Luca Ambrogioni , Umut Guclu , Marcel van Gerven

A large class of machine learning techniques requires the solution of optimization problems involving spectral functions of parametric matrices, e.g. log-determinant and nuclear norm. Unfortunately, computing the gradient of a spectral…

Machine Learning · Computer Science 2018-10-31 Insu Han , Haim Avron , Jinwoo Shin

Optimal transport distances are powerful tools to compare probability distributions and have found many applications in machine learning. Yet their algorithmic complexity prevents their direct use on large scale datasets. To overcome this…

Machine Learning · Statistics 2021-10-14 Kilian Fatras , Younes Zine , Rémi Flamary , Rémi Gribonval , Nicolas Courty

Recent work has established a path-gradient estimator for simple variational Gaussian distributions and has argued that the path-gradient is particularly beneficial in the regime in which the variational distribution approaches the exact…

Machine Learning · Computer Science 2022-06-22 Lorenz Vaitl , Kim A. Nicoli , Shinichi Nakajima , Pan Kessel

Sparse parametric models are of great interest in statistical learning and are often analyzed by means of regularized estimators. Pathwise methods allow to efficiently compute the full solution path for penalized estimators, for any…

Machine Learning · Statistics 2024-12-06 Alessandro De Gregorio , Francesco Iafrate

We obtain the optimal proxy variance for the sub-Gaussianity of Beta distribution, thus proving upper bounds recently conjectured by Elder (2016). We provide different proof techniques for the symmetrical (around its mean) case and the…

Statistics Theory · Mathematics 2017-10-18 Olivier Marchal , Julyan Arbel

Optimal transport is widely used to learn distributions, enforce distributional constraints, and model uncertainty. In applications, transport losses are often computed from samples through tractable representations, such as one-dimensional…

Optimization and Control · Mathematics 2026-05-28 Tam Le

This paper investigates the problem of tracking solutions of stochastic optimization problems with time-varying costs that depend on random variables with decision-dependent distributions. In this context, we propose the use of an online…

Optimization and Control · Mathematics 2021-10-29 Killian Wood , Gianluca Bianchin , Emiliano Dall'Anese

Flexible variational distributions improve variational inference but are harder to optimize. In this work we present a control variate that is applicable for any reparameterizable distribution with known mean and covariance matrix, e.g.…

Machine Learning · Computer Science 2020-10-26 Tomas Geffner , Justin Domke

We study the implicit regularization of gradient descent towards structured sparsity via a novel neural reparameterization, which we call a diagonally grouped linear neural network. We show the following intriguing property of our…

Machine Learning · Statistics 2023-01-31 Jiangyuan Li , Thanh V. Nguyen , Chinmay Hegde , Raymond K. W. Wong

Gaussian processes (GPs) with derivatives are useful in many applications, including Bayesian optimization, implicit surface reconstruction, and terrain reconstruction. Fitting a GP to function values and derivatives at $n$ points in $d$…

Machine Learning · Computer Science 2018-10-30 David Eriksson , Kun Dong , Eric Hans Lee , David Bindel , Andrew Gordon Wilson

This work proposes new estimators for discrete optimal transport plans that enjoy Gaussian limits centered at the true solution. This behavior stands in stark contrast with the performance of existing estimators, including those based on…

Statistics Theory · Mathematics 2025-05-08 Shuyu Liu , Florentina Bunea , Jonathan Niles-Weed

We present a new algorithm for stochastic variational inference that targets at models with non-differentiable densities. One of the key challenges in stochastic variational inference is to come up with a low-variance estimator of the…

Machine Learning · Computer Science 2018-10-26 Wonyeol Lee , Hangyeol Yu , Hongseok Yang

The reparameterization trick has become one of the most useful tools in the field of variational inference. However, the reparameterization trick is based on the standardization transformation which restricts the scope of application of…

Machine Learning · Computer Science 2020-02-26 Anbang Wu , Shuangxi Chen , Chunming Wu

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…

Optimization and Control · Mathematics 2018-10-30 Lenaic Chizat , Francis Bach

We introduce a novel optimal transport framework for probabilistic circuits (PCs). While it has been shown recently that divergences between distributions represented as certain classes of PCs can be computed tractably, to the best of our…

Artificial Intelligence · Computer Science 2025-10-16 Adrian Ciotinga , YooJung Choi