Learning and Decision-Making with Data: Optimal Formulations and Phase Transitions

• URL: http://arxiv.org/abs/2109.06911v3
• Date: Mon, 11 Mar 2024 21:28:38 GMT
• Title: Learning and Decision-Making with Data: Optimal Formulations and Phase Transitions
• Authors: Amine Bennouna and Bart P.G. Van Parys
• Abstract summary: We study the problem of designing optimal learning and decision-making formulations when only historical data is available. We show the existence of three distinct out-of-sample performance regimes.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the problem of designing optimal learning and decision-making formulations when only historical data is available. Prior work typically commits to a particular class of data-driven formulation and subsequently tries to establish out-of-sample performance guarantees. We take here the opposite approach. We define first a sensible yard stick with which to measure the quality of any data-driven formulation and subsequently seek to find an optimal such formulation. Informally, any data-driven formulation can be seen to balance a measure of proximity of the estimated cost to the actual cost while guaranteeing a level of out-of-sample performance. Given an acceptable level of out-of-sample performance, we construct explicitly a data-driven formulation that is uniformly closer to the true cost than any other formulation enjoying the same out-of-sample performance. We show the existence of three distinct out-of-sample performance regimes (a superexponential regime, an exponential regime and a subexponential regime) between which the nature of the optimal data-driven formulation experiences a phase transition. The optimal data-driven formulations can be interpreted as a classically robust formulation in the superexponential regime, an entropic distributionally robust formulation in the exponential regime and finally a variance penalized formulation in the subexponential regime. This final observation unveils a surprising connection between these three, at first glance seemingly unrelated, data-driven formulations which until now remained hidden.

Related papers

• Forecasting Outside the Box: Application-Driven Optimal Pointwise Forecasts for Stochastic Optimization [0.0]
  We present an integrated learning and optimization procedure that yields the best approximation of an unknown situation. Numerical results conducted with inventory problems from the literature as well as a bike-sharing problem with real data demonstrate that the proposed approach performs well.
  arXiv  Detail & Related papers  (2024-11-05T21:54:50Z)
• Experiment Planning with Function Approximation [49.50254688629728]
  We study the problem of experiment planning with function approximation in contextual bandit problems. We propose two experiment planning strategies compatible with function approximation. We show that a uniform sampler achieves competitive optimality rates in the setting where the number of actions is small.
  arXiv  Detail & Related papers  (2024-01-10T14:40:23Z)
• DF2: Distribution-Free Decision-Focused Learning [53.2476224456902]
  Decision-focused learning (DFL) has recently emerged as a powerful approach for predictthen-optimize problems. Existing end-to-end DFL methods are hindered by three significant bottlenecks: model error, sample average approximation error, and distribution-based parameterization of the expected objective. We present DF2 -- the first textit-free decision-focused learning method explicitly designed to address these three bottlenecks.
  arXiv  Detail & Related papers  (2023-08-11T00:44:46Z)
• Learning Unnormalized Statistical Models via Compositional Optimization [73.30514599338407]
  Noise-contrastive estimation(NCE) has been proposed by formulating the objective as the logistic loss of the real data and the artificial noise. In this paper, we study it a direct approach for optimizing the negative log-likelihood of unnormalized models.
  arXiv  Detail & Related papers  (2023-06-13T01:18:16Z)
• Data-Driven Sample Average Approximation with Covariate Information [0.0]
  We study optimization for data-driven decision-making when we have observations of the uncertain parameters within the optimization model together with concurrent observations of coparametrics. We investigate three data-driven frameworks that integrate a machine learning prediction model within a programming sample average approximation (SAA) for approximating the solution to this problem.
  arXiv  Detail & Related papers  (2022-07-27T14:45:04Z)
• Holistic Robust Data-Driven Decisions [0.0]
  Practical overfitting can typically not be attributed to a single cause but instead is caused by several factors all at once. We consider here three overfitting sources: (i) statistical error as a result of working with finite sample data, (ii) data noise which occurs when the data points are measured only with finite precision, and finally (iii) data misspecification in which a small fraction of all data may be wholly corrupted. We argue that although existing data-driven formulations may be robust against one of these three sources in isolation they do not provide holistic protection against all overfitting sources simultaneously.
  arXiv  Detail & Related papers  (2022-07-19T21:28:51Z)
• Extension of Dynamic Mode Decomposition for dynamic systems with incomplete information based on t-model of optimal prediction [69.81996031777717]
  The Dynamic Mode Decomposition has proved to be a very efficient technique to study dynamic data. The application of this approach becomes problematic if the available data is incomplete because some dimensions of smaller scale either missing or unmeasured. We consider a first-order approximation of the Mori-Zwanzig decomposition, state the corresponding optimization problem and solve it with the gradient-based optimization method.
  arXiv  Detail & Related papers  (2022-02-23T11:23:59Z)
• Learning Optimal Prescriptive Trees from Observational Data [7.215903549622416]
  We propose a method for learning optimal prescriptive trees using mixed-integer optimization (MIO) technology. Contrary to existing literature, our approach does not require data to be randomized, 2) does not impose stringent assumptions on the learned trees, and 3) has the ability to model domain specific constraints.
  arXiv  Detail & Related papers  (2021-08-31T05:38:36Z)
• Adaptive Sequential Design for a Single Time-Series [2.578242050187029]
  We learn an optimal, unknown choice of the controlled components of a design in order to optimize the expected outcome. We adapt the randomization mechanism for future time-point experiments based on the data collected on the individual over time.
  arXiv  Detail & Related papers  (2021-01-29T22:51:45Z)
• Learning while Respecting Privacy and Robustness to Distributional Uncertainties and Adversarial Data [66.78671826743884]
  The distributionally robust optimization framework is considered for training a parametric model. The objective is to endow the trained model with robustness against adversarially manipulated input data. Proposed algorithms offer robustness with little overhead.
  arXiv  Detail & Related papers  (2020-07-07T18:25:25Z)
• Causal Feature Selection for Algorithmic Fairness [61.767399505764736]
  We consider fairness in the integration component of data management. We propose an approach to identify a sub-collection of features that ensure the fairness of the dataset.
  arXiv  Detail & Related papers  (2020-06-10T20:20:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.