English
Related papers

Related papers: Unbiased Gradients for a Class of Conditional Stoc…

200 papers

Stochastic optimal control of dynamical systems is a crucial challenge in sequential decision-making. Recently, control-as-inference approaches have had considerable success, providing a viable risk-sensitive framework to address the…

Machine Learning · Computer Science 2023-12-22 Hany Abdulsamad , Sahel Iqbal , Adrien Corenflos , Simo Särkkä

We develop a framework for convexifying a fairly general class of optimization problems. Under additional assumptions, we analyze the suboptimality of the solution to the convexified problem relative to the original nonconvex problem and…

Systems and Control · Computer Science 2014-06-04 Krishnamurthy Dvijotham , Maryam Fazel , Emanuel Todorov

We use a rank one Gaussian perturbation to derive a smooth stochastic approximation of the maximum eigenvalue function. We then combine this smoothing result with an optimal smooth stochastic optimization algorithm to produce an efficient…

Optimization and Control · Mathematics 2014-03-05 Alexandre d'Aspremont , Noureddine El Karoui

This paper presents an algorithmic framework for solving unconstrained stochastic optimization problems using only stochastic function evaluations. We employ central finite-difference based gradient estimation methods to approximate the…

Optimization and Control · Mathematics 2025-01-14 Raghu Bollapragada , Cem Karamanli

Hard optimization problems are often approached by finding approximate solutions. Here, we highlight the concept of proportional sampling and discuss how it can be used to improve the performance of stochastic algorithms for optimization.…

Quantum Physics · Physics 2018-08-01 Juan Miguel Arrazola , Thomas R. Bromley , Patrick Rebentrost

Stochastic compositional optimization generalizes classic (non-compositional) stochastic optimization to the minimization of compositions of functions. Each composition may introduce an additional expectation. The series of expectations may…

Optimization and Control · Mathematics 2021-09-29 Tianyi Chen , Yuejiao Sun , Wotao Yin

Optimal stopping is the problem of deciding when to stop a stochastic system to obtain the greatest reward, arising in numerous application areas such as finance, healthcare and marketing. State-of-the-art methods for high-dimensional…

Optimization and Control · Mathematics 2020-01-01 Dragos Florin Ciocan , Velibor V. Mišić

Gradient Symbolic Computation is proposed as a means of solving discrete global optimization problems using a neurally plausible continuous stochastic dynamical system. Gradient symbolic dynamics involves two free parameters that must be…

Computation and Language · Computer Science 2018-01-12 Paul Tupper , Paul Smolensky , Pyeong Whan Cho

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…

Optimization and Control · Mathematics 2023-03-20 HanQin Cai , Daniel Mckenzie , Wotao Yin , Zhenliang Zhang

Stochastic optimization problems often involve the expectation in its objective. When risk is incorporated in the problem description as well, then risk measures have to be involved in addition to quantify the acceptable risk, often in the…

Statistics Theory · Mathematics 2012-09-18 Alois Pichler

We developed a corporative stochastic approximation (CSA) type algorithm for semi-infinite programming (SIP), where the cut generation problem is solved inexactly. First, we provide general error bounds for inexact CSA. Then, we propose two…

Optimization and Control · Mathematics 2018-12-24 Bo Wei , William B. Haskell , Sixiang Zhao

In a chance constrained program (CCP), the decision-makers aim to seek the best decision whose probability of violating the uncertainty constraints is within the prespecified risk level. As a CCP is often nonconvex and is difficult to solve…

Optimization and Control · Mathematics 2021-10-18 Nan Jiang , Weijun Xie

We propose a novel method for selective classification (SC), a problem which allows a classifier to abstain from predicting some instances, thus trading off accuracy against coverage (the fraction of instances predicted). In contrast to…

Machine Learning · Computer Science 2021-10-26 Aditya Gangrade , Anil Kag , Venkatesh Saligrama

Consider the problem of minimizing the expected value of a (possibly nonconvex) cost function parameterized by a random (vector) variable, when the expectation cannot be computed accurately (e.g., because the statistics of the random…

Multiagent Systems · Computer Science 2017-12-12 Yang Yang , Gesualdo Scutari , Daniel P. Palomar , Marius Pesavento

With this paper, we contribute to the growing research area of feature-based analysis of bio-inspired computing. In this research area, problem instances are classified according to different features of the underlying problem in terms of…

Neural and Evolutionary Computing · Computer Science 2016-02-10 Shayan Poursoltan , Frank Neumann

This paper studies stochastic optimization for a sum of compositional functions, where the inner-level function of each summand is coupled with the corresponding summation index. We refer to this family of problems as finite-sum coupled…

Optimization and Control · Mathematics 2023-06-13 Bokun Wang , Tianbao Yang

We study stochastic optimization problems with objective function given by the expectation of the maximum of two linear functions defined on the component random variables of a multivariate Gaussian distribution. We consider random…

Optimization and Control · Mathematics 2021-12-15 David Bergman , Carlos Cardonha , Jason Imbrogno , Leonardo Lozano

In this paper we consider stochastic composite convex optimization problems with the objective function satisfying a stochastic bounded gradient condition, with or without a quadratic functional growth property. These models include the…

Optimization and Control · Mathematics 2020-03-10 Ion Necoara

Chemical process optimization and control are affected by 1) plant-model mismatch, 2) process disturbances, and 3) constraints for safe operation. Reinforcement learning by policy optimization would be a natural way to solve this due to its…

We consider stochastic optimization problems which use observed data to estimate essential characteristics of the random quantities involved. Sample average approximation (SAA) or empirical (plug-in) estimation are very popular ways to use…

Statistics Theory · Mathematics 2021-03-16 Darinka Dentcheva , Yang Lin