-
作者：Agarwal, Anish; Alomar, Abdullah; Shah, Devavrat
作者单位：Columbia University; Massachusetts Institute of Technology (MIT)
摘要：We introduce and analyze two extensions of singular spectrum analysis (SSA) to the multivariate setting: a new variant of the well-known matrix-based method (mSSA) and a novel tensor-based approach (tSSA). Under a spatio-temporal factor model, we establish prediction-error guarantees for mSSA for both imputation and out-of-sample forecasting. By exploiting both spatial and temporal structure, mSSA achieves better rates than univariate SSA and standard matrix estimation methods. The out-of-samp...
-
作者：Wang, Jie; Gao, Rui; Xie, Yao
作者单位：The Chinese University of Hong Kong, Shenzhen; University of Texas System; University of Texas Austin; University System of Georgia; Georgia Institute of Technology
摘要：We study distributionally robust optimization with Sinkhorn distance: a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributions, transport costs, and loss functions. To solve the dual reformulation, we develop a stochastic mirror descent algorithm with biased subgradient estimators and derive its computational complexity guarantees. Finally, we provide numerical examples using synthetic and real data ...
-
作者：Anderson, Robert M.; Kim, Baeho; Ryu, Dean
作者单位：Harbin Institute of Technology; University of California System; University of California Berkeley; Korea University; Instituto Tecnologico Autonomo de Mexico
摘要：Estimated covariance and precision matrices of asset returns significantly influence the set of portfolios compliant with risk budgets and their potential losses. Statistical risk modeling approaches often assume temporal stability for consistency with a static factor structure, typically estimated within TM-250 days of data history, resulting in finitesample estimation error when the dimension of the population exceeds the number of observations. Our study investigates the application of Prin...
-
作者：Muhle-Karbe, Johannes; Oomen, Roel
作者单位：Imperial College London; Deutsche Bank
摘要：This paper studies a dealer that pre-hedges an anticipated potential trade, and we analyze how this affects the client's overall execution outcome. We show that prehedging can benefit both parties: Improved risk management over an extended horizon enables the dealer to charge reduced spreads that more than offset any adverse impact the pre-hedging activity has on the execution price. However, when a dealer pre-hedges too aggressively, this can be detrimental to the client. Timing uncertainty o...
-
作者：Li, Xiang; Liang, Jiadong; Chen, Xinyun; Zhang, Zhihua
作者单位：Peking University; The Chinese University of Hong Kong, Shenzhen
摘要：Stream stochastic gradient descent (SGD) is a simple and efficient method for solving online optimization problems in operations research (OR), where data are generated by parameter-dependent Markov chains. Unlike traditional approaches which require increasing batch sizes during iterations, stream SGD uses a single sample per iteration, significantly improving sample efficiency. This paper establishes a systematic framework for analyzing stream SGD, leveraging the Poisson equation solution to...
-
作者：Jiang, Shiyi; Cheng, Jianqiang; Pan, Kai; Shen, Zuo-Jun Max
作者单位：Hong Kong Polytechnic University; University of Arizona; University of California System; University of California Berkeley; University of Hong Kong; University of Hong Kong
摘要：Moment-based distributionally robust optimization (DRO) provides an optimization framework to integrate statistical information with traditional optimization approaches. Under this framework, one assumes that the underlying joint distribution of random parameters runs in a distributional ambiguity set constructed by moment information and makes decisions against the worst-case distribution within the set. Although most moment-based DRO problems can be reformulated as semidefinite programming (...
-
作者：Law, Kody . T. H.; Walton, Neil; Yang, Shangda
作者单位：University of Manchester; Durham University
摘要：We analyze the behavior of stochastic approximation algorithms where iterates, in expectation, progress toward an objective at each step. When progress is proportional to the step size of the algorithm, we prove exponential concentration bounds. These tailbounds contrast asymptotic normality results, which are more frequently associated with stochastic approximation. The methods that we develop rely on a proof of geometric ergodicity. The extends results on the exponential ergodicity of Markov...
-
作者：Haghtalab, Nika; Lykouris, Thodoris; Nietert, Sloan; Wei, Alexander
作者单位：University of California System; University of California Berkeley; Massachusetts Institute of Technology (MIT); Cornell University
摘要：We study Stackelberg games where a principal repeatedly interacts with a non-myopic long-lived agent without knowing the agent's payoff function. Although learning in Stackelberg games is well understood when the agent is myopic, dealing with non-myopic agents poses additional complications. In particular, non-myopic agents may strategize and select actions that are inferior in the present in order to mislead the principal's learning algorithm and obtain better outcomes in the future. We provi...
-
作者：Zhang, Yiyang; Liu, Junyi; Zhaoa, Xiaobo
作者单位：Tsinghua University
摘要：Focusing on stochastic programming (SP) with covariate information, this paper proposes an empirical risk minimization (ERM) method embedded within a nonconvex piecewise affine decision rule (PADR), which aims to learn the direct mapping from features to optimal decisions. We establish the nonasymptotic consistency result of our PADRbased ERM model for unconstrained problems, which illustrates the role of piece number in balancing the trade-off between the approximation and estimation errors. ...
-
作者：Vera, Alberto; Banerjee, Siddhartha; Gurvich, Itai
作者单位：Cornell University; Cornell University; Northwestern University
摘要：Theorem 3 of Vera et al. (2021) states a constant regret result for a menu-pricing problem. This erratum preserves theorem 3 but revises its proof. The revision has implications also for the assortment problem in section 5.5 of the paper.
