English
Related papers

Related papers: VarGrad: A Low-Variance Gradient Estimator for Var…

200 papers

Most zeroth-order optimization algorithms mimic a first-order algorithm but replace the gradient of the objective function with some gradient estimator that can be computed from a small number of function evaluations. This estimator is…

Optimization and Control · Mathematics 2026-01-12 Wouter Jongeneel , Man-Chung Yue , Daniel Kuhn

The recently proposed Unbiased Online Recurrent Optimization algorithm (UORO, arXiv:1702.05043) uses an unbiased approximation of RTRL to achieve fully online gradient-based learning in RNNs. In this work we analyze the variance of the…

Machine Learning · Computer Science 2019-02-08 Tim Cooijmans , James Martens

A framework to boost the efficiency of Bayesian inference in probabilistic programs is introduced by embedding a sampler inside a variational posterior approximation. We call it the refined variational approximation. Its strength lies both…

Machine Learning · Computer Science 2020-02-25 Victor Gallego , David Rios Insua

We consider unbiased estimation of a sparse nonrandom vector corrupted by additive white Gaussian noise. We show that while there are infinitely many unbiased estimators for this problem, none of them has uniformly minimum variance.…

Statistics Theory · Mathematics 2010-06-02 Alexander Jung , Zvika Ben-Haim , Franz Hlawatsch , Yonina C. Eldar

A major hurdle in machine learning is scalability to massive datasets. Approaches to overcome this hurdle include compression of the data matrix and distributing the computations. \textit{Leverage score sampling} provides a compressed…

Information Theory · Computer Science 2020-09-16 Neophytos Charalambides , Mert Pilanci , Alfred O. Hero

We propose an evolution strategies-based algorithm for estimating gradients in unrolled computation graphs, called ES-Single. Similarly to the recently-proposed Persistent Evolution Strategies (PES), ES-Single is unbiased, and overcomes…

Machine Learning · Computer Science 2023-04-24 Paul Vicol , Zico Kolter , Kevin Swersky

In machine unlearning, $(\varepsilon,\delta)-$unlearning is a popular framework that provides formal guarantees on the effectiveness of the removal of a subset of training data, the forget set, from a trained model. For strongly convex…

Machine Learning · Computer Science 2026-02-17 Martin Van Waerebeke , Marco Lorenzi , Kevin Scaman , El Mahdi El Mhamdi , Giovanni Neglia

This paper presents a new class of gradient methods for distributed machine learning that adaptively skip the gradient calculations to learn with reduced communication and computation. Simple rules are designed to detect slowly-varying…

Machine Learning · Statistics 2018-05-31 Tianyi Chen , Georgios B. Giannakis , Tao Sun , Wotao Yin

The framework of variational autoencoders (VAEs) provides a principled method for jointly learning latent-variable models and corresponding inference models. However, the main drawback of this approach is the blurriness of the generated…

Machine Learning · Computer Science 2020-07-01 Ioannis Gatopoulos , Maarten Stol , Jakub M. Tomczak

Recent studies have explored the use of deep generative models of speech spectra based of variational autoencoders (VAEs), combined with unsupervised noise models, to perform speech enhancement. These studies developed iterative algorithms…

Sound · Computer Science 2019-05-15 Manuel Pariente , Antoine Deleforge , Emmanuel Vincent

The lasso has been studied extensively as a tool for estimating the coefficient vector in the high-dimensional linear model; however, considerably less is known about estimating the error variance in this context. In this paper, we propose…

Methodology · Statistics 2019-07-22 Guo Yu , Jacob Bien

We wish to compute the gradient of an expectation over a finite or countably infinite sample space having $K \leq \infty$ categories. When $K$ is indeed infinite, or finite but very large, the relevant summation is intractable. Accordingly,…

Machine Learning · Statistics 2019-05-14 Runjing Liu , Jeffrey Regier , Nilesh Tripuraneni , Michael I. Jordan , Jon McAuliffe

In this article, we highlight what appears to be major issue of Variational Autoencoders, evinced from an extensive experimentation with different network architectures and datasets: the variance of generated data is significantly lower…

Machine Learning · Computer Science 2020-05-26 Andrea Asperti

The construction of loss functions presents a major challenge in data-driven modeling involving weak-form operators in PDEs and gradient flows, particularly due to the need to select test functions appropriately. We address this challenge…

Machine Learning · Statistics 2025-12-16 Yuan Gao , Quanjun Lang , Fei Lu

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

Variational Autoencoders (VAEs) have become a cornerstone in generative modeling and representation learning within machine learning. This paper explores a nuanced aspect of VAEs, focusing on interpreting the Kullback-Leibler (KL)…

Machine Learning · Computer Science 2024-06-25 Mariano Rivera

Variance reduction is a family of powerful mechanisms for stochastic optimization that appears to be helpful in many machine learning tasks. It is based on estimating the exact gradient with some recursive sequences. Previously, many papers…

Optimization and Control · Mathematics 2025-11-07 Aleksandr Shestakov , Valery Parfenov , Aleksandr Beznosikov

Gradient matching is a promising tool for learning parameters and state dynamics of ordinary differential equations. It is a grid free inference approach, which, for fully observable systems is at times competitive with numerical…

Machine Learning · Statistics 2018-04-11 Nico S. Gorbach , Stefan Bauer , Joachim M. Buhmann

The score function estimator is widely used for estimating gradients of stochastic objectives in stochastic computation graphs (SCG), eg, in reinforcement learning and meta-learning. While deriving the first-order gradient estimators by…

Machine Learning · Computer Science 2018-11-07 Jakob Foerster , Gregory Farquhar , Maruan Al-Shedivat , Tim Rocktäschel , Eric P. Xing , Shimon Whiteson

In this paper we propose an extension of the classical Sobol' estimator for the estimation of variance based sensitivity indices. The approach assumes a linear correlation model between the input variables which is used to decompose the…

Methodology · Statistics 2024-08-12 Thomas Most