English
Related papers

Related papers: Understanding the Variance Dichotomy in Continuous…

200 papers

We consider derivative-free black-box global optimization of expensive noisy functions, when most of the randomness in the objective is produced by a few influential scalar random inputs. We present a new Bayesian global optimization…

Machine Learning · Computer Science 2016-02-23 Saul Toscano-Palmerin , Peter I. Frazier

Reliability-based design optimization (RBDO) is traditionally formulated as a nested optimization and reliability problem. Although surrogate models are generally employed to improve efficiency, the approach remains computationally…

Computation · Statistics 2026-04-08 M. Moustapha , B. Sudret

We consider the problem of stochastic convex optimization under convex constraints. We analyze the behavior of a natural variance reduced proximal gradient (VRPG) algorithm for this problem. Our main result is a non-asymptotic guarantee for…

Optimization and Control · Mathematics 2024-04-02 Koulik Khamaru

Stochastic constraints, which incorporate both deterministic parameters and random variables, extend classical deterministic constraints by explicitly accounting for uncertainty. These constraints are increasingly prevalent in data science,…

Logic in Computer Science · Computer Science 2026-04-21 Xiakun Li , Hao Wu , Bican Xia , Tengshun Yang , Naijun Zhan

Contextual Bayesian Optimization (CBO) efficiently optimizes black-box functions with respect to design variables, while simultaneously integrating contextual information regarding the environment, such as experimental conditions. However,…

In this paper we propose a variant of a consensus-based global optimization (CBO) method that uses personal best information in order to compute the global minimum of a non-convex, locally Lipschitz continuous function. The proposed…

Optimization and Control · Mathematics 2020-08-25 Claudia Totzeck , Marie-Therese Wolfram

Unbiased and consistent variance estimators generally do not exist for design-based treatment effect estimators because experimenters never observe more than one potential outcome for any unit. The problem is exacerbated by interference and…

Methodology · Statistics 2024-07-04 Christopher Harshaw , Joel A. Middleton , Fredrik Sävje

Variational inequalities are a universal optimization paradigm that is interesting in itself, but also incorporates classical minimization and saddle point problems. Modern realities encourage to consider stochastic formulations of…

Optimization and Control · Mathematics 2024-03-27 Alexander Pichugin , Maksim Pechin , Aleksandr Beznosikov , Alexander Gasnikov

We prove a general existence result in stochastic optimal control in discrete time where controls take values in conditional metric spaces, and depend on the current state and the information of past decisions through the evolution of a…

Optimization and Control · Mathematics 2018-12-19 Asgar Jamneshan , Michael Kupper , José Miguel Zapata

Maximum surjective constraint satisfaction problems (Max-Sur-CSPs) are computational problems where we are given a set of variables denoting values from a finite domain B and a set of constraints on the variables. A solution to such a…

Computational Complexity · Computer Science 2011-10-14 Walter Bach , Hang Zhou

In this thesis, I study the minimax oracle complexity of distributed stochastic optimization. First, I present the "graph oracle model", an extension of the classic oracle complexity framework that can be applied to study distributed…

Optimization and Control · Mathematics 2021-09-03 Blake Woodworth

Offline reinforcement learning aims to learn from pre-collected datasets without active exploration. This problem faces significant challenges, including limited data availability and distributional shifts. Existing approaches adopt a…

Machine Learning · Computer Science 2024-10-01 Yue Wang , Jinjun Xiong , Shaofeng Zou

Stochastic compositional optimization arises in many important machine learning tasks such as value function evaluation in reinforcement learning and portfolio management. The objective function is the composition of two expectations of…

Machine Learning · Statistics 2020-01-28 Huizhuo Yuan , Xiangru Lian , Ji Liu

Future- or return-conditioned supervised learning is an emerging paradigm for offline reinforcement learning (RL), where the future outcome (i.e., return) associated with an observed action sequence is used as input to a policy trained to…

Machine Learning · Computer Science 2022-10-25 Mengjiao Yang , Dale Schuurmans , Pieter Abbeel , Ofir Nachum

In a typical optimization problem, the task is to pick one of a number of options with the lowest cost or the highest value. In practice, these cost/value quantities often come through processes such as measurement or machine learning,…

Data Structures and Algorithms · Computer Science 2022-07-20 Mohammad Mahdian , Jieming Mao , Kangning Wang

We consider the problem of fitting variational posterior approximations using stochastic optimization methods. The performance of these approximations depends on (1) how well the variational family matches the true posterior…

In this paper, we analyze the accuracy of gradient estimates obtained by linear interpolation when the underlying function is subject to bounded measurement noise. The total gradient error is decomposed into a deterministic component…

Numerical Analysis · Mathematics 2025-07-29 Alejandro G. Marchetti , Dominique Bonvin

Robust topology optimization (RTO), as a class of topology optimization problems, identifies a design with the best average performance while reducing the response sensitivity to input uncertainties, e.g. load uncertainty. Solving RTO is…

Machine Learning · Computer Science 2024-08-22 Rini Jasmine Gladstone , Mohammad Amin Nabian , Vahid Keshavarzzadeh , Hadi Meidani

Distributionally Robust Optimization (DRO) is a worst-case approach to decision making when there is model uncertainty. It is also well known that for certain uncertainty sets, DRO is approximated by a regularized nominal problem. We show…

Optimization and Control · Mathematics 2026-05-08 Jun-ya Gotoh , Michael Jong Kim , Andrew E. B. Lim

High-probability guarantees in stochastic optimization are often obtained only under strong noise assumptions such as sub-Gaussian tails. We show that such guarantees can also be achieved under the weaker assumption of bounded variance by…

Optimization and Control · Mathematics 2025-12-23 Jiaming Liang