Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Faury, Louis"'
Logistic Bandits have recently undergone careful scrutiny by virtue of their combined theoretical and practical relevance. This research effort delivered statistically efficient algorithms, improving the regret of previous strategies by exponentially
Externí odkaz:
http://arxiv.org/abs/2201.01985
Generalized Linear Bandits (GLBs) are powerful extensions to the Linear Bandit (LB) setting, broadening the benefits of reward parametrization beyond linearity. In this paper we study GLBs in non-stationary environments, characterized by a general me
Externí odkaz:
http://arxiv.org/abs/2103.05750
This paper extends the Distributionally Robust Optimization (DRO) approach for offline contextual bandits. Specifically, we leverage this framework to introduce a convex reformulation of the Counterfactual Risk Minimization principle. Besides relying
Externí odkaz:
http://arxiv.org/abs/2011.06835
Publikováno v:
AISTATS 2021 - International Conference on Artificial Intelligence and Statistics, Apr 2021, San Diego / Virtual, United States
Contextual sequential decision problems with categorical or numerical observations are ubiquitous and Generalized Linear Bandits (GLB) offer a solid theoretical framework to address them. In contrast to the case of linear bandits, existing algorithms
Externí odkaz:
http://arxiv.org/abs/2011.00819
Logistic Bandits have recently attracted substantial attention, by providing an uncluttered yet challenging framework for understanding the impact of non-linearity in parametrized bandits. It was shown by Faury et al. (2020) that the learning-theoret
Externí odkaz:
http://arxiv.org/abs/2010.12642
The generalized linear bandit framework has attracted a lot of attention in recent years by extending the well-understood linear setting and allowing to model richer reward structures. It notably covers the logistic model, widely used when rewards ar
Externí odkaz:
http://arxiv.org/abs/2002.07530
This manuscript introduces the idea of using Distributionally Robust Optimization (DRO) for the Counterfactual Risk Minimization (CRM) problem. Tapping into a rich existing literature, we show that DRO is a principled tool for counterfactual decision
Externí odkaz:
http://arxiv.org/abs/1906.06211
Evolutionary Strategies (ES) are a popular family of black-box zeroth-order optimization algorithms which rely on search distributions to efficiently optimize a large variety of objective functions. This paper investigates the potential benefits of u
Externí odkaz:
http://arxiv.org/abs/1901.11271
The aim of global optimization is to find the global optimum of arbitrary classes of functions, possibly highly multimodal ones. In this paper we focus on the subproblem of global optimization for differentiable functions and we propose an Evolutiona
Externí odkaz:
http://arxiv.org/abs/1805.08594
Autor:
Faury, Louis, Vasile, Flavian
Learning to optimize - the idea that we can learn from data algorithms that optimize a numerical criterion - has recently been at the heart of a growing number of research efforts. One of the most challenging issues within this approach is to learn a
Externí odkaz:
http://arxiv.org/abs/1801.07222