English
Related papers

Related papers: The Importance of Pessimism in Fixed-Dataset Polic…

200 papers

Prediction sets can wrap around any ML model to cover unknown test outcomes with a guaranteed probability. Yet, it remains unclear how to use them optimally for downstream decision-making. Here, we propose a decision-theoretic framework…

Machine Learning · Statistics 2026-02-10 Tao Wang , Edgar Dobriban

Our goal is to build robust optimization problems for making decisions based on complex data from the past. In robust optimization (RO) generally, the goal is to create a policy for decision-making that is robust to our uncertainty about…

Optimization and Control · Mathematics 2014-07-07 Theja Tulabandhula , Cynthia Rudin

It is becoming increasingly apparent that probabilistic approaches can overcome conservatism and computational complexity of the classical worst-case deterministic framework and may lead to designs that are actually safer. In this paper we…

Applications · Statistics 2008-11-01 Xinjia Chen , Kemin Zhou , Jorge L. Aravena

We study offline reinforcement learning (RL) in partially observable Markov decision processes. In particular, we aim to learn an optimal policy from a dataset collected by a behavior policy which possibly depends on the latent state. Such…

Machine Learning · Computer Science 2024-04-02 Miao Lu , Yifei Min , Zhaoran Wang , Zhuoran Yang

There is growing importance to detecting faults and implementing the best methods in industrial and real-world systems. We are searching for the most trustworthy and practical data-based fault detection methods proposed by artificial…

Systems and Control · Electrical Eng. & Systems 2023-01-11 Mohammad Hossein Modirrousta , Mahdi Aliyari Shoorehdeli , Mostafa Yari , Arash Ghahremani

While maximizing expected return is the goal in most reinforcement learning approaches, risk-sensitive objectives such as conditional value at risk (CVaR) are more suitable for many high-stakes applications. However, relatively little is…

Machine Learning · Computer Science 2020-04-06 Ramtin Keramati , Christoph Dann , Alex Tamkin , Emma Brunskill

Existing approaches of prescriptive analytics -- where inputs of an optimization model can be predicted by leveraging covariates in a machine learning model -- often attempt to optimize the mean value of an uncertain objective. However,…

Machine Learning · Computer Science 2025-03-05 Dimitris Bertsimas , Benjamin Boucher

We study offline dynamic pricing when historical data provide incomplete coverage of the price space such that some candidate prices, including the optimal one, may be entirely unobserved. This setting is common in practice and is…

Machine Learning · Statistics 2026-05-25 Zeyu Bian , Lan Wang , Zhengling Qi

An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well as a given baseline strategy. In this paper, we develop and…

Machine Learning · Statistics 2016-07-14 Marek Petrik , Yinlam Chow , Mohammad Ghavamzadeh

Optimization is offered as an objective approach to resolving complex, real-world decisions involving uncertainty and conflicting interests. It drives business strategies as well as public policies and, increasingly, lies at the heart of…

Artificial Intelligence · Computer Science 2023-08-01 Benjamin Laufer , Thomas Krendl Gilbert , Helen Nissenbaum

Algorithms often have tunable parameters that impact performance metrics such as runtime and solution quality. For many algorithms used in practice, no parameter settings admit meaningful worst-case bounds, so the parameters are made…

Machine Learning · Computer Science 2021-04-27 Maria-Florina Balcan , Dan DeBlasio , Travis Dick , Carl Kingsford , Tuomas Sandholm , Ellen Vitercik

The classical approach to system identification is based on stochastic assumptions about the measurement error, and provides estimates that have random nature. Worst-case identification, on the other hand, only assumes the knowledge of…

Systems and Control · Computer Science 2013-06-07 Fabrizio Dabbene , Mario Sznaier , Roberto Tempo

Inference-time computation offers a powerful axis for scaling the performance of language models. However, naively increasing computation in techniques like Best-of-N sampling can lead to performance degradation due to reward hacking.…

Artificial Intelligence · Computer Science 2025-04-09 Audrey Huang , Adam Block , Qinghua Liu , Nan Jiang , Akshay Krishnamurthy , Dylan J. Foster

In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes the probability of a catastrophic failure. Unfortunately,…

Machine Learning · Computer Science 2021-03-01 Elita A. Lobo , Mohammad Ghavamzadeh , Marek Petrik

Prediction models are often employed in estimating parameters of optimization models. Despite the fact that in an end-to-end view, the real goal is to achieve good optimization performance, the prediction performance is measured on its own.…

Optimization and Control · Mathematics 2021-01-01 Nam Ho-Nguyen , Fatma Kılınç-Karzan

Policy optimization algorithms are crucial in many fields but challenging to grasp and implement, often due to complex calculations related to Markov decision processes and varying use of discount and average reward setups. This paper…

Systems and Control · Electrical Eng. & Systems 2025-04-07 Shuang Wu

Evaluating and optimizing policies in the presence of unobserved confounders is a problem of growing interest in offline reinforcement learning. Using conventional methods for offline RL in the presence of confounding can not only lead to…

Machine Learning · Statistics 2023-11-08 Chinmaya Kausik , Yangyi Lu , Kevin Tan , Maggie Makar , Yixin Wang , Ambuj Tewari

Machine learning algorithms typically rely on optimization subroutines and are well-known to provide very effective outcomes for many types of problems. Here, we flip the reliance and ask the reverse question: can machine learning…

Machine Learning · Computer Science 2019-07-30 Jesus A. De Loera , Jamie Haddock , Anna Ma , Deanna Needell

Stochastic optimization is a widely used approach for optimization under uncertainty, where uncertain input parameters are modeled by random variables. Exact or approximation algorithms have been obtained for several fundamental problems in…

Machine Learning · Computer Science 2025-08-14 Arpit Agarwal , Rohan Ghuge , Viswanath Nagarajan , Zhengjia Zhuo

We introduce algorithms that use predictions from machine learning applied to the input to circumvent worst-case analysis. We aim for algorithms that have near optimal performance when these predictions are good, but recover the…

Data Structures and Algorithms · Computer Science 2020-06-17 Michael Mitzenmacher , Sergei Vassilvitskii