English
Related papers

Related papers: Low-variance Black-box Gradient Estimates for the …

200 papers

We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output…

Machine Learning · Statistics 2017-11-01 Yihao Feng , Dilin Wang , Qiang Liu

This paper presents a control variate-based Markov chain Monte Carlo algorithm for efficient sampling from the probability simplex, with a focus on applications in large-scale Bayesian models such as latent Dirichlet allocation. Standard…

Methodology · Statistics 2024-10-02 Francesco Barile , Christopher Nemeth

In physics and engineering, many processes are modeled using non-differentiable black-box simulators, making the optimization of such functions particularly challenging. To address such cases, inspired by the Gradient Theorem, we propose…

In this paper, we propose new listwise learning-to-rank models that mitigate the shortcomings of existing ones. Existing listwise learning-to-rank models are generally derived from the classical Plackett-Luce model, which has three major…

Information Retrieval · Computer Science 2020-01-24 Xiaofeng Zhu , Diego Klabjan

Model predictive control (MPC) schemes have a proven track record for delivering aggressive and robust performance in many challenging control tasks, coping with nonlinear system dynamics, constraints, and observational noise. Despite their…

Robotics · Computer Science 2024-01-24 Lucas Barcelos , Alexander Lambert , Rafael Oliveira , Paulo Borges , Byron Boots , Fabio Ramos

We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings that arise naturally in finance, economics, and operations…

Machine Learning · Computer Science 2025-12-18 Hanqing Jin , Renyuan Xu , Yanzhao Yang

We present a multilevel stochastic gradient descent method for the optimal control of systems governed by partial differential equations under uncertain input data. The gradient descent method used to find the optimal control leverages a…

Optimization and Control · Mathematics 2025-06-04 Niklas Baumgarten , David Schneiderhan

The Frank-Wolfe optimization algorithm has recently regained popularity for machine learning applications due to its projection-free property and its ability to handle structured constraints. However, in the stochastic learning setting, it…

Machine Learning · Computer Science 2017-09-15 Elad Hazan , Haipeng Luo

Structured latent variables allow incorporating meaningful prior knowledge into deep learning models. However, learning with such variables remains challenging because of their discrete nature. Nowadays, the standard learning approach is to…

Machine Learning · Computer Science 2021-10-29 Kirill Struminsky , Artyom Gadetsky , Denis Rakitin , Danil Karpushkin , Dmitry Vetrov

Rank-based metrics are some of the most widely used criteria for performance evaluation of computer vision models. Despite years of effort, direct optimization for these metrics remains a challenge due to their non-differentiable and…

Machine Learning · Computer Science 2024-12-16 Michal Rolínek , Vít Musil , Anselm Paulus , Marin Vlastelica , Claudio Michaelis , Georg Martius

We systematically develop a learning-based treatment of stochastic optimal control (SOC), relying on direct optimization of parametric control policies. We propose a derivation of adjoint sensitivity results for stochastic differential…

Machine Learning · Computer Science 2021-06-08 Stefano Massaroli , Michael Poli , Stefano Peluchetti , Jinkyoo Park , Atsushi Yamashita , Hajime Asama

Stochastic gradient descent is a classic algorithm that has gained great popularity especially in the last decades as the most common approach for training models in machine learning. While the algorithm has been well-studied when…

Machine Learning · Statistics 2025-09-09 Jose Blanchet , Aleksandar Mijatović , Wenhao Yang

In the vanishing learning rate regime, stochastic gradient descent (SGD) is now relatively well understood. In this work, we propose to study the basic properties of SGD and its variants in the non-vanishing learning rate regime. The focus…

Machine Learning · Statistics 2021-06-14 Kangqiao Liu , Liu Ziyin , Masahito Ueda

Optimization problems with continuous data appear in, e.g., robust machine learning, functional data analysis, and variational inference. Here, the target function is given as an integral over a family of (continuously) indexed target…

Machine Learning · Computer Science 2023-11-01 Kexin Jin , Jonas Latz , Chenguang Liu , Carola-Bibiane Schönlieb

Low-variance gradient estimation is crucial for learning directed graphical models parameterized by neural networks, where the reparameterization trick is widely used for those with continuous variables. While this technique gives…

Machine Learning · Statistics 2016-11-07 Seiya Tokui , Issei sato

In this paper we present a novel approach towards variance reduction for discretised diffusion processes. The proposed approach involves specially constructed control variates and allows for a significant reduction in the variance for the…

Probability · Mathematics 2017-09-19 Denis Belomestny , Stefan Häfner , Tigran Nagapetyan , Mikhail Urusov

Black Box Variational Inference is a promising framework in a succession of recent efforts to make Variational Inference more ``black box". However, in basic version it either fails to converge due to instability or requires some…

Machine Learning · Computer Science 2024-05-10 Dominic B. Dayta

Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data. This might degrade the convergence by yielding estimates that suffer from a high variance. A possible…

Machine Learning · Statistics 2018-06-07 Zalán Borsos , Andreas Krause , Kfir Y. Levy

In this paper we present an enhancement of the regression-based variance reduction approaches recently proposed in Belomestny et al. This enhancement is based on a truncation of the control variate and allows for a significant reduction of…

Probability · Mathematics 2017-11-10 Denis Belomestny , Stefan Häfner , Mikhail Urusov

This paper considers a distributed stochastic strongly convex optimization, where agents connected over a network aim to cooperatively minimize the average of all agents' local cost functions. Due to the stochasticity of gradient estimation…

Optimization and Control · Mathematics 2020-02-17 Jinlong Lei , Peng Yi , Jie Chen , Yiguang Hong