中文
相关论文

相关论文: On the Impossibility of Statistically Improving Em…

200 篇论文

Stochastic optimization problems often involve data distributions that change in reaction to the decision variables. This is the case for example when members of the population respond to a deployed classifier by manipulating their features…

最优化与控制 · 数学 2020-12-15 Dmitriy Drusvyatskiy , Lin Xiao

Comparisons of different treatments or production processes are the goals of a significant fraction of applied research. Unsurprisingly, two-sample problems play a main role in Statistics through natural questions such as `Is the the new…

统计方法学 · 统计学 2017-09-05 P. C. Álvarez-Esteban , E. del Barrio , J. A. Cuesta-Albertos , C. Matrán

We propose a statistically optimal approach to construct data-driven decisions for stochastic optimization problems. Fundamentally, a data-driven decision is simply a function that maps the available training data to a feasible action. It…

最优化与控制 · 数学 2023-12-18 Tobias Sutter , Bart P. G. Van Parys , Daniel Kuhn

In data-driven optimization, solution feasibility is often ensured through a "safe" reformulation of the uncertain constraints, such that an obtained data-driven solution is guaranteed to be feasible for the oracle formulation with high…

最优化与控制 · 数学 2019-09-17 Henry Lam , Huajie Qian

This contribution examines optimization problems that involve stochastic dominance constraints. These problems have uncountably many constraints. We develop methods to solve the optimization problem by reducing the constraints to a finite…

最优化与控制 · 数学 2025-02-27 Rajmadan Lakshmanan , Alois Pichler , Miloš Kopa

In performative prediction, the choice of a model influences the distribution of future data, typically through actions taken based on the model's predictions. We initiate the study of stochastic optimization for performative prediction.…

机器学习 · 计算机科学 2021-02-22 Celestine Mendler-Dünner , Juan C. Perdomo , Tijana Zrnic , Moritz Hardt

Many stochastic optimization problems include chance constraints that enforce constraint satisfaction with a specific probability; however, solving an optimization problem with chance constraints assumes that the solver has access to the…

最优化与控制 · 数学 2021-09-21 Joshua Comden , Ahmed S. Zamzam , Andrey Bernstein

Optimal prediction (OP) methods compensate for a lack of resolution in the numerical solution of complex problems through the use of an invariant measure as a prior measure in the Bayesian sense. In first-order OP, unresolved information is…

数值分析 · 数学 2025-10-20 John Bell , Alexandre J. Chorin , William Crutchfield

We consider the problem of analyzing the probabilistic performance of first-order methods when solving convex optimization problems drawn from an unknown distribution only accessible through samples. By combining performance estimation…

最优化与控制 · 数学 2025-12-11 Jisun Park , Vinit Ranjan , Bartolomeo Stellato

Motivated by emerging applications in machine learning, we consider an optimization problem in a general form where the gradient of the objective function is available through a biased stochastic oracle. We assume a bias-control parameter…

最优化与控制 · 数学 2026-02-10 Yin Liu , Sam Davanloo Tajbakhsh

Optimal control under uncertainty is a prevailing challenge for many reasons. One of the critical difficulties lies in producing tractable solutions for the underlying stochastic optimization problem. We show how advanced approximate…

机器学习 · 计算机科学 2024-10-28 Joe Watson , Hany Abdulsamad , Rolf Findeisen , Jan Peters

We study the effect of stochasticity in on-policy policy optimization, and make the following four contributions. First, we show that the preferability of optimization methods depends critically on whether stochastic versus exact gradients…

机器学习 · 计算机科学 2021-11-01 Jincheng Mei , Bo Dai , Chenjun Xiao , Csaba Szepesvari , Dale Schuurmans

We design an algorithm which finds an $\epsilon$-approximate stationary point (with $\|\nabla F(x)\|\le \epsilon$) using $O(\epsilon^{-3})$ stochastic gradient and Hessian-vector products, matching guarantees that were previously available…

机器学习 · 计算机科学 2020-06-25 Yossi Arjevani , Yair Carmon , John C. Duchi , Dylan J. Foster , Ayush Sekhari , Karthik Sridharan

While data-driven decision-making is transforming modern operations, most large-scale data is of an observational nature, such as transactional records. These data pose unique challenges in a variety of operational problems posed as…

最优化与控制 · 数学 2017-05-23 Dimitris Bertsimas , Nathan Kallus

We provide a novel computer-assisted technique for systematically analyzing first-order methods for optimization. In contrast with previous works, the approach is particularly suited for handling sublinear convergence rates and stochastic…

最优化与控制 · 数学 2021-12-22 Adrien Taylor , Francis Bach

In this paper we deal with stochastic optimization problems where the data distributions change in response to the decision variables. Traditionally, the study of optimization problems with decision-dependent distributions has assumed…

最优化与控制 · 数学 2023-10-05 Zifan Wang , Changxin Liu , Thomas Parisini , Michael M. Zavlanos , Karl H. Johansson

Stochastic dominance serves as a general framework for modeling a broad spectrum of decision preferences under uncertainty, with risk aversion as one notable example, as it naturally captures the intrinsic structure of the underlying…

机器学习 · 计算机科学 2026-01-06 Shicong Cen , Jincheng Mei , Hanjun Dai , Dale Schuurmans , Yuejie Chi , Bo Dai

In performative stochastic optimization, decisions can influence the distribution of random parameters, rendering the data-generating process itself decision-dependent. In practice, decision-makers rarely have access to the true…

最优化与控制 · 数学 2025-10-27 Zhuangzhuang Jia , Yijie Wang , Roy Dong , Grani A. Hanasusanto

Supported by the recent contributions in multiple branches, the first-order splitting algorithms became central for structured nonsmooth optimization. In the large-scale or noisy contexts, when only stochastic information on the smooth part…

最优化与控制 · 数学 2020-10-05 Andrei Patrascu , Paul Irofti

Optimization under uncertainty deals with the problem of optimizing stochastic cost functions given some partial information on their inputs. These problems are extremely difficult to solve and yet pervade all areas of technological and…

‹ 上一页 1 2 3 10 下一页 ›