中文
相关论文

相关论文: Rao-Blackwellized Stochastic Gradients for Discret…

200 篇论文

We introduce a hybrid stochastic estimator to design stochastic gradient algorithms for solving stochastic optimization problems. Such a hybrid estimator is a convex combination of two existing biased and unbiased estimators and leads to…

最优化与控制 · 数学 2019-05-16 Quoc Tran-Dinh , Nhan H. Pham , Dzung T. Phan , Lam M. Nguyen

We show that unconverged stochastic gradient descent can be interpreted as a procedure that samples from a nonparametric variational approximate posterior distribution. This distribution is implicitly defined as the transformation of an…

机器学习 · 统计学 2015-04-07 Dougal Maclaurin , David Duvenaud , Ryan P. Adams

Derivative-free optimization has become an important technique used in machine learning for optimizing black-box models. To conduct updates without explicitly computing gradient, most current approaches iteratively sample a random search…

机器学习 · 统计学 2018-08-03 Liu Liu , Minhao Cheng , Cho-Jui Hsieh , Dacheng Tao

We consider a regularized expected reward optimization problem in the non-oblivious setting that covers many existing problems in reinforcement learning (RL). In order to solve such an optimization problem, we apply and analyze the…

机器学习 · 计算机科学 2024-08-21 Ling Liang , Haizhao Yang

Sampling is an important tool for estimating large, complex sums and integrals over high dimensional spaces. For instance, important sampling has been used as an alternative to exact methods for inference in belief networks. Ideally, we…

人工智能 · 计算机科学 2013-01-18 Luis E. Ortiz , Leslie Pack Kaelbling

This paper investigates distributed zeroth-order optimization for smooth nonconvex problems, targeting the trade-off between convergence rate and sampling cost per zeroth-order gradient estimation in current algorithms that use either the…

最优化与控制 · 数学 2026-04-10 Huaiyi Mu , Yujie Tang , Jie Song , Zhongkui Li

We study distributed optimization problems over a network when the communication between the nodes is constrained, and so information that is exchanged between the nodes must be quantized. This imperfect communication poses a fundamental…

最优化与控制 · 数学 2018-10-30 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg

Gradient-based optimization methods are commonly used to identify local optima in high-dimensional spaces. When derivatives cannot be evaluated directly, stochastic estimators can provide approximate gradients. However, these estimators'…

机器学习 · 计算机科学 2026-02-03 Philipp Andelfinger , Wentong Cai

Standard variational lower bounds used to train latent variable models produce biased estimates of most quantities of interest. We introduce an unbiased estimator of the log marginal likelihood and its gradients for latent variable models…

机器学习 · 计算机科学 2020-07-14 Yucen Luo , Alex Beatson , Mohammad Norouzi , Jun Zhu , David Duvenaud , Ryan P. Adams , Ricky T. Q. Chen

In this paper, we propose a random gradient-free method for optimization in infinite dimensional Hilbert spaces, applicable to functional optimization in diverse settings. Though such problems are often solved through finite-dimensional…

最优化与控制 · 数学 2025-12-25 Caio Lins Peixoto , Daniel Csillag , Bernardo F. P. da Costa , Yuri F. Saporito

In this paper we consider the estimation of unknown parameters in Bayesian inverse problems. In most cases of practical interest, there are several barriers to performing such estimation, This includes a numerical approximation of a…

统计方法学 · 统计学 2025-02-07 Neil K. Chada , Ajay Jasra , Mohamed Maama , Raul Tempone

Large dimensional least-squares and regularised least-squares problems are expensive to solve. There exist many approximate techniques, some deterministic (like conjugate gradient), some stochastic (like stochastic gradient descent). Among…

信号处理 · 电气工程与系统科学 2021-10-18 Yusuf Pilavcı , Pierre-Olivier Amblard , Simon Barthelmé , Nicolas Tremblay

We introduce a family of pairwise stochastic gradient estimators for gradients of expectations, which are related to the log-derivative trick, but involve pairwise interactions between samples. The simplest example of our new estimator,…

机器学习 · 计算机科学 2022-04-21 Christian J. Walder , Paul Roussel , Richard Nock , Cheng Soon Ong , Masashi Sugiyama

We consider the problem of minimizing a high-dimensional objective function, which may include a regularization term, using (possibly noisy) evaluations of the function. Such optimization is also called derivative-free, zeroth-order, or…

最优化与控制 · 数学 2023-03-20 HanQin Cai , Daniel Mckenzie , Wotao Yin , Zhenliang Zhang

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.,…

机器学习 · 计算机科学 2013-05-15 Yoshua Bengio

We propose an unbiased Monte-Carlo estimator for $\mathbb{E}[g(X_{t_1}, \cdots, X_{t_n})]$, where $X$ is a diffusion process defined by a multi-dimensional stochastic differential equation (SDE). The main idea is to start instead from a…

概率论 · 数学 2016-03-08 Pierre Henry-Labordere , Xiaolu Tan , Nizar Touzi

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…

机器学习 · 计算机科学 2019-02-08 Tim Cooijmans , James Martens

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…

最优化与控制 · 数学 2020-02-17 Jinlong Lei , Peng Yi , Jie Chen , Yiguang Hong

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.…

机器学习 · 计算机科学 2018-11-16 Sergey Pankov

We propose an extragradient method with stepsizes bounded away from zero for stochastic variational inequalities requiring only pseudo-monotonicity. We provide convergence and complexity analysis, allowing for an unbounded feasible set,…

最优化与控制 · 数学 2017-03-02 Alfredo Iusem , Alejandro Jofré , Roberto I. Oliveira , Philip Thompson