English
Related papers

Related papers: Variance reduction properties of the reparameteriz…

200 papers

Reparameterization of variational auto-encoders with continuous random variables is an effective method for reducing the variance of their gradient estimates. In the discrete case, one can perform reparametrization using the Gumbel-Max…

Machine Learning · Computer Science 2019-12-10 Guy Lorberbom , Andreea Gane , Tommi Jaakkola , Tamir Hazan

Variational methods are widely used for approximate posterior inference. However, their use is typically limited to families of distributions that enjoy particular conjugacy properties. To circumvent this limitation, we propose a family of…

Machine Learning · Computer Science 2012-06-22 Samuel Gershman , Matt Hoffman , David Blei

Importance weighted variational inference (VI) approximates densities known up to a normalizing constant by optimizing bounds that tighten with the number of Monte Carlo samples $N$. Standard optimization relies on reparameterized gradient…

Machine Learning · Statistics 2026-02-03 Kamélia Daudel , Minh-Ngoc Tran , Cheng Zhang

Gradient regularization (GR) is a method that penalizes the gradient norm of the training loss during training. While some studies have reported that GR can improve generalization performance, little attention has been paid to it from the…

Machine Learning · Computer Science 2023-02-06 Ryo Karakida , Tomoumi Takase , Tomohiro Hayase , Kazuki Osawa

In this paper we focus on the linear functionals defining an approximate version of the gradient of a function. These functionals are often used when dealing with optimization problems where the computation of the gradient of the objective…

Optimization and Control · Mathematics 2021-05-21 Marco Boresta , Tommaso Colombo , Alberto De Santis , Stefano Lucidi

Diffusion models have achieved remarkable success across diverse domains, but they remain vulnerable to memorization -- reproducing training data rather than generating novel outputs. This not only limits their creative potential but also…

Machine Learning · Statistics 2025-11-10 Zeqi Ye , Qijie Zhu , Molei Tao , Minshuo Chen

We consider the problem of minimizing the sum of two convex functions: one is the average of a large number of smooth component functions, and the other is a general convex function that admits a simple proximal mapping. We assume the whole…

Optimization and Control · Mathematics 2014-03-20 Lin Xiao , Tong Zhang

Probabilistic graphical models are a key tool in machine learning applications. Computing the partition function, i.e., normalizing constant, is a fundamental task of statistical inference but it is generally computationally intractable,…

Machine Learning · Statistics 2020-01-29 Sungsoo Ahn , Michael Chertkov , Adrian Weller , Jinwoo Shin

Finite sample size corrections to the reparametrization-invariant solution of the inverse problem of probability are computed, and shown to converge uniformly to the correct distribution.

adap-org · Physics 2007-05-23 Vipul Periwal

The Gumbel trick is a method to sample from a discrete probability distribution, or to estimate its normalizing partition function. The method relies on repeatedly applying a random perturbation to the distribution in a particular way, each…

Machine Learning · Statistics 2017-06-14 Matej Balog , Nilesh Tripuraneni , Zoubin Ghahramani , Adrian Weller

Models with a large number of latent variables are often used to fully utilize the information in big or complex data. However, they can be difficult to estimate using standard approaches, and variational inference methods are a popular…

Methodology · Statistics 2021-04-20 Rubén Loaiza-Maya , Michael Stanley Smith , David J. Nott , Peter J. Danaher

Amortized inference allows latent-variable models trained via variational learning to scale to large datasets. The quality of approximate inference is determined by two factors: a) the capacity of the variational distribution to match the…

Machine Learning · Computer Science 2018-05-29 Chris Cremer , Xuechen Li , David Duvenaud

Gaussian distributions are widely used in Bayesian variational inference to approximate intractable posterior densities, but the ability to accommodate skewness can improve approximation accuracy significantly, when data or prior…

Methodology · Statistics 2025-02-05 Linda S. L. Tan , Aoxiang Chen

The method of statistical differentials, which approximates the mean and variance of transformations of random variables is used in many areas of mathematics. This paper will discuss the conditions under which such an approximation will be…

Probability · Mathematics 2007-05-23 Rohitha Goonatilake

Consider a Gaussian nonparametric regression problem having both an unknown mean function and unknown variance function. This article presents a class of difference-based kernel estimators for the variance function. Optimal convergence…

Statistics Theory · Mathematics 2009-09-29 Lawrence D. Brown , M. Levine

Random features (RFs) are a popular technique to scale up kernel methods in machine learning, replacing exact kernel evaluations with stochastic Monte Carlo estimates. They underpin models as diverse as efficient transformers (by…

Machine Learning · Statistics 2024-10-04 Isaac Reid , Stratis Markou , Krzysztof Choromanski , Richard E. Turner , Adrian Weller

Are score function estimators an underestimated approach to learning with $k$-subset sampling? Sampling $k$-subsets is a fundamental operation in many machine learning tasks that is not amenable to differentiable parametrization, impeding…

Machine Learning · Computer Science 2024-08-19 Klas Wijk , Ricardo Vinuesa , Hossein Azizpour

Variational Optimization forms a differentiable upper bound on an objective. We show that approaches such as Natural Evolution Strategies and Gaussian Perturbation, are special cases of Variational Optimization in which the expectations are…

Machine Learning · Statistics 2018-09-14 Thomas Bird , Julius Kunze , David Barber

We consider the semi-parametric estimation of a scale parameter of a one-dimensional Gaussian process with known smoothness. We suggest an estimator based on quadratic variations and on the moment method. We provide asymptotic…

Statistics Theory · Mathematics 2020-01-22 Jean-Marc Azaïs , François Bachoc , Agnès Lagnoux , Thi Mong Ngoc Nguyen

Structured variational inference constitutes a core methodology in modern statistical applications. Unlike mean-field variational inference, the approximate posterior is assumed to have interdependent structure. We consider the natural…

Machine Learning · Statistics 2025-11-14 Shunan Sheng , Bohan Wu , Bennett Zhu , Sinho Chewi , Aram-Alexandre Pooladian
‹ Prev 1 4 5 6 7 8 10 Next ›