English
Related papers

Related papers: Sticking the Landing: Simple, Lower-Variance Gradi…

200 papers

Variational inference uses optimization, rather than integration, to approximate the marginal likelihood, and thereby the posterior, in a Bayesian model. Thanks to advances in computational scalability made in the last decade, variational…

Machine Learning · Statistics 2023-01-04 Jens Sjölund

We propose a novel study of the stochastic proximal gradient method for minimizing the sum of two convex functions, one of which is smooth. Under suitable assumptions and without requiring any boundedness or control of the variance of the…

Optimization and Control · Mathematics 2026-04-16 Javier I. Madariaga

To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variable augmentation,…

Machine Learning · Statistics 2019-12-24 Mingzhang Yin , Yuguang Yue , Mingyuan Zhou

In this paper, we propose an adaptive finite difference scheme in order to numerically solve total variation type problems for image processing tasks. The automatic generation of the grid relies on indicators derived from a local estimation…

Numerical Analysis · Mathematics 2024-10-18 Thomas Jacumin , Andreas Langer

We present a new algorithm for approximate inference in probabilistic programs, based on a stochastic gradient for variational programs. This method is efficient without restrictions on the probabilistic program; it is particularly…

Machine Learning · Statistics 2013-01-08 David Wingate , Theophane Weber

We consider reduced-rank modeling of the white noise covariance matrix in a large dimensional vector autoregressive (VAR) model. We first propose the reduced-rank covariance estimator under the setting where independent observations are…

Applications · Statistics 2014-12-09 Richard A. Davis , Pengfei Zang , Tian Zheng

We present a general method for deriving collapsed variational inference algo- rithms for probabilistic models in the conjugate exponential family. Our method unifies many existing approaches to collapsed variational inference. Our…

Machine Learning · Computer Science 2012-12-05 James Hensman , Magnus Rattray , Neil D. Lawrence

Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one. Recently, boosting variational inference has been proposed as a new paradigm to approximate the posterior by a…

Machine Learning · Computer Science 2018-03-08 Francesco Locatello , Rajiv Khanna , Joydeep Ghosh , Gunnar Rätsch

In this paper, we introduce a novel method to generate interpretable regression function estimators. The idea is based on called data-dependent coverings. The aim is to extract from the data a covering of the feature space instead of a…

Statistics Theory · Mathematics 2021-01-27 Vincent Margot , Jean-Patrick Baudry , Frédéric Guilloux , Olivier Wintenberger

Mean-field variational inference is a method for approximate Bayesian posterior inference. It approximates a full posterior distribution with a factorized set of distributions by maximizing a lower bound on the marginal likelihood. This…

Machine Learning · Computer Science 2012-07-03 John Paisley , David Blei , Michael Jordan

Recent advances in the literature have demonstrated that standard supervised learning algorithms are ill-suited for problems with endogenous explanatory variables. To correct for the endogeneity bias, many variants of nonparameteric…

Econometrics · Economics 2021-01-18 Edvard Bakhitov , Amandeep Singh

Sampling is an important tool for estimating large, complex sums and integrals over high dimensional spaces. For instance, important sampling has been used as an alternative to exact methods for inference in belief networks. Ideally, we…

Artificial Intelligence · Computer Science 2013-01-18 Luis E. Ortiz , Leslie Pack Kaelbling

Estimating the test performance of a model, possibly under distribution shift, without having access to the ground-truth labels is a challenging, yet very important problem for the safe deployment of machine learning algorithms in the wild.…

Machine Learning · Computer Science 2025-05-13 Renchunzi Xie , Ambroise Odonnat , Vasilii Feofanov , Ievgen Redko , Jianfeng Zhang , Bo An

Many probabilistic models that have an intractable normalizing constant may be extended to contain covariates. Since the evaluation of the exact likelihood is difficult or even impossible for these models, score matching was proposed to…

Statistics Theory · Mathematics 2022-03-21 Jiazhen Xu , Janice L. Scealy , Andrew T. A. Wood , Tao Zou

Despite the empirical success of meta reinforcement learning (meta-RL), there are still a number poorly-understood discrepancies between theory and practice. Critically, biased gradient estimates are almost always implemented in practice,…

Machine Learning · Computer Science 2021-12-15 Yunhao Tang

We propose a novel computationally low-cost method for estimating a general predictive measure of generalised Bayesian inference. The proposed method utilises posterior covariance and provides estimators of the Gibbs and the plugin…

Methodology · Statistics 2025-01-14 Yukito Iba , Keisuke Yano

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

Online Learning to Rank (OL2R) algorithms learn from implicit user feedback on the fly. The key of such algorithms is an unbiased estimation of gradients, which is often (trivially) achieved by uniformly sampling from the entire parameter…

Information Retrieval · Computer Science 2019-11-18 Huazheng Wang , Sonwoo Kim , Eric McCord-Snook , Qingyun Wu , Hongning Wang

We introduce local expectation gradients which is a general purpose stochastic variational inference algorithm for constructing stochastic gradients through sampling from the variational distribution. This algorithm divides the problem of…

Machine Learning · Statistics 2015-03-06 Michalis K. Titsias

Recent studies show that transformer-based architectures emulate gradient descent during a forward pass, contributing to in-context learning capabilities - an ability where the model adapts to new tasks based on a sequence of prompt…

Statistics Theory · Mathematics 2024-05-13 Karthik Duraisamy