English
Related papers

Related papers: Coupled Gradient Estimators for Discrete Latent Va…

200 papers

We provide a new computationally-efficient class of estimators for risk minimization. We show that these estimators are robust for general statistical models: in the classical Huber epsilon-contamination model and in heavy-tailed settings.…

Machine Learning · Statistics 2018-04-23 Adarsh Prasad , Arun Sai Suggala , Sivaraman Balakrishnan , Pradeep Ravikumar

Estimating the score, i.e., the gradient of log density function, from a set of samples generated by an unknown distribution is a fundamental task in inference and learning of probabilistic models that involve flexible yet intractable…

Machine Learning · Statistics 2020-07-01 Yuhao Zhou , Jiaxin Shi , Jun Zhu

Coreference evaluation metrics are hard to optimize directly as they are non-differentiable functions, not easily decomposable into elementary decisions. Consequently, most approaches optimize objectives only indirectly related to the end…

Computation and Language · Computer Science 2017-06-23 Phong Le , Ivan Titov

Stochastic kinetic models are ubiquitous in physics, yet inferring their parameters from experimental data remains challenging. In deterministic models, parameter inference often relies on gradients, as they can be obtained efficiently…

Computational Physics · Physics 2026-04-03 Ludwig Burger , Annalena Kofler , Lukas Heinrich , Ulrich Gerland

Recent variational inference methods use stochastic gradient estimators whose variance is not well understood. Theoretical guarantees for these estimators are important to understand when these methods will or will not work. This paper…

Machine Learning · Computer Science 2019-10-29 Justin Domke

Categorical regressor variables are usually handled by introducing a set of indicator variables, and imposing a linear constraint to ensure identifiability in the presence of an intercept, or equivalently, using one of various coding…

Computation · Statistics 2018-05-21 Felicitas J. Detmer , Martin Slawski

Stochastic gradient descent (SGD), which dates back to the 1950s, is one of the most popular and effective approaches for performing stochastic optimization. Research on SGD resurged recently in machine learning for optimizing convex loss…

Machine Learning · Computer Science 2019-12-24 Jie Chen , Ronny Luss

We present efficient finite difference estimators for goal-oriented sensitivity indices with applications to the generalized Langevin equation (GLE). In particular, we apply these estimators to analyze an extended variable formulation of…

Numerical Analysis · Mathematics 2018-09-18 Eric Joseph Hall , Markos A. Katsoulakis , Luc Rey-Bellet

Reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models with human preferences. However, policy gradient methods such as PPO suffer from high variance gradient estimates,…

Machine Learning · Computer Science 2026-01-21 Lukas Abrie Nel

Stochastic neurons can be useful for a number of reasons in deep learning models, but in many cases they pose a challenging problem: how to estimate the gradient of a loss function with respect to the input of such stochastic neurons, i.e.,…

Machine Learning · Computer Science 2013-05-15 Yoshua Bengio

Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model…

Machine Learning · Computer Science 2026-05-01 Nghia Bui , Lijing Wang

Variable selection is essential in high-dimensional data analysis. Although various variable selection methods have been developed, most rely on the linear model assumption. This article proposes a nonparametric variable selection method…

Machine Learning · Statistics 2021-09-30 Jongkyeong Kang , Seung Jun Shin

Recent progress in deep latent variable models has largely been driven by the development of flexible and scalable variational inference methods. Variational training of this type involves maximizing a lower bound on the log-likelihood,…

Machine Learning · Computer Science 2016-06-02 Andriy Mnih , Danilo J. Rezende

Calibration of large-scale differential equation models to observational or experimental data is a widespread challenge throughout applied sciences and engineering. A crucial bottleneck in state-of-the art calibration methods is the…

Optimization and Control · Mathematics 2021-02-23 Jon Cockayne , Andrew B. Duncan

Categorical random variables can faithfully represent the discrete and uncertain aspects of data as part of a discrete latent variable model. Learning in such models necessitates taking gradients with respect to the parameters of the…

Machine Learning · Computer Science 2023-11-22 Lennert De Smet , Emanuele Sansone , Pedro Zuidberg Dos Martires

Within many machine learning algorithms, a fundamental problem concerns efficient calculation of an unbiased gradient wrt parameters $\gammav$ for expectation-based objectives $\Ebb_{q_{\gammav} (\yv)} [f(\yv)]$. Most existing methods…

Machine Learning · Statistics 2019-01-21 Yulai Cong , Miaoyun Zhao , Ke Bai , Lawrence Carin

Gradient-based optimization is the foundation of deep learning and reinforcement learning. Even when the mechanism being optimized is unknown or not differentiable, optimization using high-variance or biased gradient estimates is still…

Machine Learning · Computer Science 2018-02-27 Will Grathwohl , Dami Choi , Yuhuai Wu , Geoffrey Roeder , David Duvenaud

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

Overparameterized stochastic differential equation (SDE) models have achieved remarkable success in various complex environments, such as PDE-constrained optimization, stochastic control and reinforcement learning, financial engineering,…

Optimization and Control · Mathematics 2024-09-27 Shengbo Wang , Jose Blanchet , Peter Glynn

The partitioning of data for estimation and calibration critically impacts the performance of propensity score based estimators like inverse probability weighting (IPW) and double/debiased machine learning (DML) frameworks. We extend recent…

Machine Learning · Statistics 2025-05-20 Sven Klaassen , Jan Rabenseifner , Jannis Kueck , Philipp Bach