中文
相关论文

相关论文: A unified view of likelihood ratio and reparameter…

200 篇论文

Reparameterization (RP) and likelihood ratio (LR) gradient estimators are used to estimate gradients of expectations throughout machine learning and reinforcement learning; however, they are usually explained as simple mathematical tricks,…

机器学习 · 计算机科学 2021-06-01 Paavo Parmas , Masashi Sugiyama

Variational inference using the reparameterization trick has enabled large-scale approximate Bayesian inference in complex probabilistic models, leveraging stochastic optimization to sidestep intractable expectations. The reparameterization…

机器学习 · 统计学 2020-02-13 Christian A. Naesseth , Francisco J. R. Ruiz , Scott W. Linderman , David M. Blei

ReParameterization (RP) Policy Gradient Methods (PGMs) have been widely adopted for continuous control tasks in robotics and computer graphics. However, recent studies have revealed that, when applied to long-term reinforcement learning…

机器学习 · 计算机科学 2023-11-01 Shenao Zhang , Boyi Liu , Zhaoran Wang , Tuo Zhao

The probabilistic diffusion model (DM), generating content by inferencing through a recursive chain structure, has emerged as a powerful framework for visual generation. After pre-training on enormous data, the model needs to be properly…

计算机视觉与模式识别 · 计算机科学 2025-09-30 Tao Ren , Zishi Zhang , Jingyang Jiang , Zehao Li , Shentao Qin , Yi Zheng , Guanghao Li , Qianyou Sun , Yan Li , Jiafeng Liang , Xinping Li , Yijie Peng

The reparameterization gradient has become a widely used method to obtain Monte Carlo gradients to optimize the variational objective. However, this technique does not easily apply to commonly used distributions such as beta or gamma…

机器学习 · 统计学 2016-10-20 Francisco J. R. Ruiz , Michalis K. Titsias , David M. Blei

In high-dimensional statistics, variable selection recovers the latent sparse patterns from all possible covariate combinations. This paper proposes a novel optimization method to solve the exact L0-regularized regression problem, which is…

统计方法学 · 统计学 2022-06-02 Mingzhang Yin , Nhat Ho , Bowei Yan , Xiaoning Qian , Mingyuan Zhou

We observe that gradients computed via the reparameterization trick are in direct correspondence with solutions of the transport equation in the formalism of optimal transport. We use this perspective to compute (approximate) pathwise…

机器学习 · 统计学 2018-07-06 Martin Jankowiak , Fritz Obermeyer

In many fields of science, generalized likelihood ratio tests are established tools for statistical inference. At the same time, it has become increasingly common that a simulator (or generative model) is used to describe complex processes…

应用统计 · 统计学 2016-03-21 Kyle Cranmer , Juan Pavez , Gilles Louppe

By providing a simple and efficient way of computing low-variance gradients of continuous random variables, the reparameterization trick has become the technique of choice for training a variety of latent variable models. However, it is not…

机器学习 · 计算机科学 2019-01-31 Michael Figurnov , Shakir Mohamed , Andriy Mnih

Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate (low bias) gradient estimator is crucial to face…

机器学习 · 计算机科学 2021-07-21 João Carvalho , Davide Tateo , Fabio Muratore , Jan Peters

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…

机器学习 · 统计学 2016-11-07 Seiya Tokui , Issei sato

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…

机器学习 · 统计学 2021-07-14 Matthias Bauer , Andriy Mnih

The reparameterization trick is widely used in variational inference as it yields more accurate estimates of the gradient of the variational objective than alternative approaches such as the score function method. Although there is…

机器学习 · 统计学 2018-12-31 Ming Xu , Matias Quiroz , Robert Kohn , Scott A. Sisson

Efficient and biologically plausible alternatives to backpropagation in neural network training remain a challenge due to issues such as high computational complexity and additional assumptions about neural networks, which limit scalability…

机器学习 · 计算机科学 2024-03-20 Zeliang Zhang , Jinyang Jiang , Zhuo Liu , Susan Liang , Yijie Peng , Chenliang Xu

Seeking to improve model generalization, we consider a new approach based on distributionally robust learning (DRL) that applies stochastic gradient descent to the outer minimization problem. Our algorithm efficiently estimates the gradient…

机器学习 · 统计学 2020-12-24 Soumyadip Ghosh , Mark Squillante

Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparameterization gradients, or gradient estimates computed via the "reparameterization trick," represent a class of noisy gradients often used in…

机器学习 · 统计学 2017-05-23 Andrew C. Miller , Nicholas J. Foti , Alexander D'Amour , Ryan P. Adams

Latent Gaussian variables have been popularised in probabilistic machine learning. In turn, gradient estimators are the machinery that facilitates gradient-based optimisation for models with latent Gaussian variables. The reparameterisation…

机器学习 · 统计学 2025-10-21 Kevin H. Lam , Thang D. Bui , George Deligiannidis , Yee Whye Teh

Variational inference approximates the posterior distribution of a probabilistic model with a parameterized density by maximizing a lower bound for the model evidence. Modern solutions fit a flexible approximation with stochastic gradient…

机器学习 · 统计学 2017-07-13 Joseph Sakaya , Arto Klami

Gaussian graphical modeling has been widely used to explore various network structures, such as gene regulatory networks and social networks. We often use a penalized maximum likelihood approach with the $L_1$ penalty for learning a…

统计方法学 · 统计学 2017-06-13 Kei Hirose , Hironori Fujisawa , Jun Sese

We study the foundations of variational inference, which frames posterior inference as an optimisation problem, for probabilistic programming. The dominant approach for optimisation in practice is stochastic gradient descent. In particular,…

编程语言 · 计算机科学 2023-01-10 Basim Khajwal , C. -H. Luke Ong , Dominik Wagner
‹ 上一页 1 2 3 10 下一页 ›