English
Related papers

Related papers: Rao-Blackwellizing the Straight-Through Gumbel-Sof…

200 papers

When evaluating and comparing models using leave-one-out cross-validation (LOO-CV), the uncertainty of the estimate is typically assessed using the variance of the sampling distribution. Considering the uncertainty is important, as the…

Methodology · Statistics 2022-02-16 Tuomas Sivula , Måns Magnusson , Aki Vehtari

The simplest and most widely applied method for guaranteeing differential privacy is to add instance-independent noise to a statistic of interest that is scaled to its global sensitivity. However, global sensitivity is a worst-case notion…

Statistics Theory · Mathematics 2019-06-10 Mark Bun , Thomas Steinke

We consider the problem of minimizing the average of a large number of smooth but possibly non-convex functions. In the context of most machine learning applications, each loss function is non-negative and thus can be expressed as the…

Optimization and Control · Mathematics 2024-07-08 Antonio Orvieto , Lin Xiao

In neural network models, soft mixtures of fixed candidate components (e.g., logic gates and sub-networks) are often used during training for stable optimization, while hard selection is typically used at inference. This raises questions…

Machine Learning · Computer Science 2026-03-17 Youngsung Kim

Standard practice obtains an unbiased variance estimator by dividing by $N-1$ rather than $N$. Yet if only half the data are used to compute the mean, dividing by $N$ can still yield an unbiased estimator. We show that an alternative mean…

Statistics Theory · Mathematics 2025-04-10 Dai Akita

Motivated by surprisingly good generalization properties of learned deep neural networks in overparameterized scenarios and by the related double descent phenomenon, this paper analyzes the relation between smoothness and low generalization…

Machine Learning · Computer Science 2021-10-29 Yuege Xie , Hung-Hsu Chou , Holger Rauhut , Rachel Ward

Efficient low-variance gradient estimation enabled by the reparameterization trick (RT) has been essential to the success of variational autoencoders. Doubly-reparameterized gradients (DReGs) improve on the RT for multi-sample variational…

Machine Learning · Statistics 2021-07-14 Matthias Bauer , Andriy Mnih

We compute precise asymptotic expressions for the learning curves of least squares random feature (RF) models with either a separable strongly convex regularization or the $\ell_1$ regularization. We propose a novel multi-level application…

Machine Learning · Statistics 2023-03-02 David Bosch , Ashkan Panahi , Ayca Özcelikkale , Devdatt Dubhash

Recent work shows that path gradient estimators for normalizing flows have lower variance compared to standard estimators for variational inference, resulting in improved training. However, they are often prohibitively more expensive from a…

Machine Learning · Computer Science 2024-03-26 Lorenz Vaitl , Ludwig Winkler , Lorenz Richter , Pan Kessel

The validity of estimation and smoothing parameter selection for the wide class of generalized additive models for location, scale and shape (GAMLSS) relies on the correct specification of a likelihood function. Deviations from such…

Methodology · Statistics 2019-11-14 William H. Aeberhard , Eva Cantoni , Giampiero Marra , Rosalba Radice

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

Gaussian process regression is used throughout statistics and machine learning for prediction and uncertainty quantification. A Gaussian process is specified by its mean and covariance functions. Many covariance functions, including…

Statistics Theory · Mathematics 2025-10-28 Toni Karvonen , François Bachoc

Deep latent variable models have become a popular model choice due to the scalable learning algorithms introduced by (Kingma & Welling, 2013; Rezende et al., 2014). These approaches maximize a variational lower bound on the intractable log…

Machine Learning · Computer Science 2018-11-20 George Tucker , Dieterich Lawson , Shixiang Gu , Chris J. Maddison

Key to effective generic, or "black-box", variational inference is the selection of an approximation to the target density that balances accuracy and speed. Copula models are promising options, but calibration of the approximation can be…

Methodology · Statistics 2022-07-01 Michael Stanley Smith , Rubén Loaiza-Maya

Simulations are becoming ever more common as a tool for designing complex products. Sensitivity analysis techniques can be applied to these simulations to gain insight, or to reduce the complexity of the problem at hand. However, these…

Other Computer Science · Computer Science 2017-02-03 Tom Van Steenkiste , Joachim van der Herten , Ivo Couckuyt , Tom Dhaene

Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance in gradient estimation, resulting in poor sample efficiency.…

Machine Learning · Computer Science 2018-11-16 Sergey Pankov

This paper introduces a unified family of smoothed quantile estimators that continuously interpolate between classical empirical quantiles and the sample mean. The estimators q(z, h) are defined as minimizers of a regularized objective…

Methodology · Statistics 2025-10-31 Saïd Maanan , Azzouz Dermoune , Ahmed El Ghini

Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning and vision fields. The validity of existing works heavily relies on solving a series of approximation subproblems with extraordinarily high…

Optimization and Control · Mathematics 2022-05-23 Risheng Liu , Xuan Liu , Wei Yao , Shangzhi Zeng , Jin Zhang

Large and performant neural networks are often overparameterized and can be drastically reduced in size and complexity thanks to pruning. Pruning is a group of methods, which seeks to remove redundant or unnecessary weights or groups of…

Computer Vision and Pattern Recognition · Computer Science 2023-02-15 Robin Dupont , Mohammed Amine Alaoui , Hichem Sahbi , Alice Lebois

General ridge estimators are widely used in the general linear model because they possess desirable properties such as linear sufficiency and linear admissibility. However, when the covariance matrix of the error term is partially unknown,…

Statistics Theory · Mathematics 2026-01-27 Hirai Mukasa
‹ Prev 1 8 9 10 Next ›