English
Related papers

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

200 papers

We study a linear high-dimensional regression model in a semi-supervised setting, where for many observations only the vector of covariates $X$ is given with no response $Y$. We do not make any sparsity assumptions on the vector of…

Statistics Theory · Mathematics 2021-09-03 Ilan Livne , David Azriel , Yair Goldberg

A variance reduction technique in nonparametric smoothing is proposed: at each point of estimation, form a linear combination of a preliminary estimator evaluated at nearby points with the coefficients specified so that the asymptotic bias…

Statistics Theory · Mathematics 2007-08-22 Ming-Yen Cheng , Liang Peng , Jyh-Shyang Wu

As a structured prediction task, scene graph generation, given an input image, aims to explicitly model objects and their relationships by constructing a visually-grounded scene graph. In the current literature, such task is universally…

Computer Vision and Pattern Recognition · Computer Science 2022-06-24 Daqi Liu , Miroslaw Bober , Josef Kittler

The statistics and machine learning communities have recently seen a growing interest in classification-based approaches to two-sample testing. The outcome of a classification-based two-sample test remains a rejection decision, which is not…

Statistics Theory · Mathematics 2022-11-15 Loris Michel , Jeffrey Näf , Nicolai Meinshausen

In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external…

Machine Learning · Computer Science 2016-01-06 John Schulman , Nicolas Heess , Theophane Weber , Pieter Abbeel

This paper aims at achieving a "good" estimator for the gradient of a function on a high-dimensional space. Often such functions are not sensitive in all coordinates and the gradient of the function is almost sparse. We propose a method for…

Machine Learning · Statistics 2016-07-27 Vivek S. Borkar , Vikranth R. Dwaracherla , Neeraja Sahasrabudhe

Several variational bounds involving importance weighting ideas generalize the Evidence Lower BOund (ELBO) for marginal likelihood optimization, such as the Importance-weighted Auto-Encoder (IWAE), Variational R\'enyi (VR) and VR-IWAE…

Machine Learning · Statistics 2026-05-28 Kamélia Daudel , François Roueff

Natural-gradient methods enable fast and simple algorithms for variational inference, but due to computational difficulties, their use is mostly limited to \emph{minimal} exponential-family (EF) approximations. In this paper, we extend…

Machine Learning · Statistics 2020-11-09 Wu Lin , Mohammad Emtiyaz Khan , Mark Schmidt

Inference networks of traditional Variational Autoencoders (VAEs) are typically amortized, resulting in relatively inaccurate posterior approximation compared to instance-wise variational optimization. Recent semi-amortized approaches were…

Machine Learning · Computer Science 2020-11-18 Minyoung Kim , Vladimir Pavlovic

Variational inference transforms posterior inference into parametric optimization thereby enabling the use of latent variable models where otherwise impractical. However, variational inference can be finicky when different variational…

Machine Learning · Computer Science 2019-12-03 Da Tang , Rajesh Ranganath

We propose a new way of training neural networks, with the goal of reducing training cost. Our method uses approximate predicted gradients instead of the full gradients that require an expensive backward pass. We derive a…

Machine Learning · Computer Science 2025-11-10 Kamil Ciosek , Nicolò Felicioni , Juan Elenter Litwin

Motivated by a wide variety of applications, ranging from stochastic optimization to dimension reduction through variable selection, the problem of estimating gradients accurately is of crucial importance in statistics and learning theory.…

Machine Learning · Computer Science 2020-06-29 Guillaume Ausset , Stephan Clémençon , François Portier

We propose using model reparametrization to improve variational Bayes inference for hierarchical models whose variables can be classified as global (shared across observations) or local (observation specific). Posterior dependence between…

Methodology · Statistics 2021-01-28 Linda S. L. Tan

In this paper we introduce a family of stochastic gradient estimation techniques based of the perturbative expansion around the mean of the sampling distribution. We characterize the bias and variance of the resulting Taylor-corrected…

Machine Learning · Statistics 2019-11-18 Luca Ambrogioni , Marcel A. J. van Gerven

The ability to backpropagate stochastic gradients through continuous latent distributions has been crucial to the emergence of variational autoencoders and stochastic gradient variational Bayes. The key ingredient is an unbiased and…

Neural and Evolutionary Computing · Computer Science 2016-07-20 Alex Graves

Current literature on posterior approximation for Bayesian inference offers many alternative methods. Does our chosen approximation scheme work well on the observed data? The best existing generic diagnostic tools treating this kind of…

Computation · Statistics 2020-06-22 Hanwen Xing , Geoff K. Nicholls , Jeong Eun Lee

Variance estimation is important for statistical inference. It becomes non-trivial when observations are masked by serial dependence structures and time-varying mean structures. Existing methods either ignore or sub-optimally handle these…

Methodology · Statistics 2022-01-03 Kin Wai Chan

Gradient-based approximate inference methods, such as Stein variational gradient descent (SVGD), provide simple and general-purpose inference engines for differentiable continuous distributions. However, existing forms of SVGD cannot be…

Machine Learning · Computer Science 2020-03-03 Jun Han , Fan Ding , Xianglong Liu , Lorenzo Torresani , Jian Peng , Qiang Liu

We study stochastic zeroth order gradient and Hessian estimators for real-valued functions in $\mathbb{R}^n$. We show that, via taking finite difference along random orthogonal directions, the variance of the stochastic finite difference…

Machine Learning · Computer Science 2023-06-07 Yasong Feng , Tianyu Wang

Gradient matching with Gaussian processes is a promising tool for learning parameters of ordinary differential equations (ODE's). The essence of gradient matching is to model the prior over state variables as a Gaussian process which…

Machine Learning · Statistics 2016-10-25 Nico S. Gorbach , Stefan Bauer , Joachim M. Buhmann