English
Related papers

Related papers: Efficient Policy Learning from Surrogate-Loss Clas…

200 papers

An efficient policy search algorithm should estimate the local gradient of the objective function, with respect to the policy parameters, from as few trials as possible. Whereas most policy search methods estimate this gradient by observing…

Artificial Intelligence · Computer Science 2012-06-18 Gregory Lawrence , Stuart Russell

Many prediction domains, such as ad placement, recommendation, trajectory prediction, and document summarization, require predicting a set or list of options. Such lists are often evaluated using submodular reward functions that measure…

Machine Learning · Computer Science 2013-05-14 Stephane Ross , Jiaji Zhou , Yisong Yue , Debadeepta Dey , J. Andrew Bagnell

Many policies allocate harms or benefits that are uncertain in nature: they produce distributions over the population in which individuals have different probabilities of incurring harm or benefit. Comparing different policies thus involves…

Computers and Society · Computer Science 2021-03-11 Hoda Heidari , Solon Barocas , Jon Kleinberg , Karen Levy

We study the problem of classification with a reject option for a fixed predictor, applicable in natural language processing. We introduce a new problem formulation for this scenario, and an algorithm minimizing a new surrogate loss…

Machine Learning · Computer Science 2023-02-01 Christopher Mohri , Daniel Andor , Eunsol Choi , Michael Collins

Learning in a lifelong setting, where the dynamics continually evolve, is a hard challenge for current reinforcement learning algorithms. Yet this would be a much needed feature for practical applications. In this paper, we propose an…

Machine Learning · Computer Science 2021-12-14 Pierre Liotet , Francesco Vidaich , Alberto Maria Metelli , Marcello Restelli

Transfer learning of prediction models has been extensively studied, while the corresponding policy learning approaches are rarely discussed. In this paper, we propose principled approaches for learning the optimal policy in the target…

Machine Learning · Computer Science 2025-05-20 Xueqing Liu , Qinwei Yang , Zhaoqing Tian , Ruocheng Guo , Peng Wu

Prediction+optimization is a common real-world paradigm where we have to predict problem parameters before solving the optimization problem. However, the criteria by which the prediction model is trained are often inconsistent with the goal…

Machine Learning · Computer Science 2021-11-23 Kai Yan , Jie Yan , Chuan Luo , Liting Chen , Qingwei Lin , Dongmei Zhang

Strategic classification, i.e. classification under possible strategic manipulations of features, has received a lot of attention from both the machine learning and the game theory community. Most works focus on analysing properties of the…

Machine Learning · Computer Science 2022-03-28 Tosca Lechner , Ruth Urner

Performative learning addresses the increasingly pervasive situations in which algorithmic decisions may induce changes in the data distribution as a consequence of their public deployment. We propose a novel view in which these…

Machine Learning · Computer Science 2024-11-05 Edwige Cyffers , Muni Sreenivas Pydi , Jamal Atif , Olivier Cappé

Constructing decision trees online is a classical machine learning problem. Existing works often assume that features are readily available for each incoming data point. However, in many real world applications, both feature values and the…

Machine Learning · Computer Science 2025-06-18 Arman Rahbar , Ziyu Ye , Yuxin Chen , Morteza Haghir Chehreghani

We consider a class of stochastic programming problems where the implicitly decision-dependent random variable follows a nonparametric regression model with heteroscedastic error. The Clarke subdifferential and surrogate functions are not…

Optimization and Control · Mathematics 2025-05-13 Boyang Shen , Junyi Liu

We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem is often a critical step when applying RL…

Machine Learning · Computer Science 2016-05-27 Nan Jiang , Lihong Li

Reinforcement learning provides a mathematical framework for learning-based control, whose success largely depends on the amount of data it can utilize. The efficient utilization of historical trajectories obtained from previous policies is…

Machine Learning · Computer Science 2025-03-06 Yifan Lin , Yuhao Wang , Enlu Zhou

We study the problem of deriving policies, or rules, that when enacted on a complex system, cause a desired outcome. Absent the ability to perform controlled experiments, such rules have to be inferred from past observations of the system's…

Machine Learning · Computer Science 2020-09-09 Kailash Budhathoki , Mario Boley , Jilles Vreeken

Distributionally robust policy learning aims to find a policy that performs well under the worst-case distributional shift, and yet most existing methods for robust policy learning consider the worst-case joint distribution of the covariate…

Machine Learning · Computer Science 2025-06-03 Jingyuan Wang , Zhimei Ren , Ruohan Zhan , Zhengyuan Zhou

In many real-world machine learning problems, feature values are not readily available. To make predictions, some of the missing features have to be acquired, which can incur a cost in money, computational time, or human time, depending on…

Machine Learning · Computer Science 2019-12-20 Kimmo Kärkkäinen , Mohammad Kachuee , Orpaz Goldstein , Majid Sarrafzadeh

We discuss a new weighted likelihood method for parametric estimation. The method is motivated by the need for generating a simple estimation strategy which provides a robust solution that is simultaneously fully efficient when the model is…

Methodology · Statistics 2019-08-29 Suman Majumder , Adhidev Biswas , Tania Roy , Subir Kumar Bhandari , Ayanendranath Basu

Causal effect estimation from observational data is a challenging problem, especially with high dimensional data and in the presence of unobserved variables. The available data-driven methods for tackling the problem either provide an…

Methodology · Statistics 2022-07-25 Debo Cheng , Jiuyong Li , Lin Liu , Jiji Zhang , Jixue Liu , Thuc Duy Le

We investigate optimal order execution problems in discrete time with instantaneous price impact and stochastic resilience. First, in the setting of linear transient price impact we derive a closed-form recursion for the optimal strategy,…

Trading and Market Microstructure · Quantitative Finance 2023-10-31 Tao Chen , Mike Ludkovski , Moritz Voß

Structural failure time models are causal models for estimating the effect of time-varying treatments on a survival outcome. G-estimation and artificial censoring have been proposed to estimate the model parameters in the presence of…

Methodology · Statistics 2019-02-19 Shu Yang , Karen Pieper , Frank Cools