Skip to Main content Skip to Navigation

Adaptive methods for optimization in stochastic environments

Xuedong Shang 1, 2, 3, 4, 5
4 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
5 Scool - Scool
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : Imagine that we have access to a simulator that models the behaviour of some complex numerical task. Being considered as a black box, we can only get useful information by running the simulator with different inputs. For example, the process of inferring the 3D structure of a protein from its amino-acid sequence can be regarded as such a complex task, that can be modelled by a simulator. The inputs of the simulator are the amino-acid sequences and the outputs are the predicted 3D structures. A popular family of methods seek to optimize a suitable energy function – produced by the simulator – that describes the relation between the structure of a protein and its amino-acid sequence. These meth- ods are of interest because they are able to build protein structures without prior knowl- edge on solved structures.In this thesis, we model the previous scenarios as a sequential optimization problem under stochastic environments. At each round, we can query a data point from the environment, and receive a noisy reward. We first focus on the case where the environment is abstracted as a finite search space, then we investigate also on a more general setting where the environment is composed of an infinite number of points or even continuous. In both cases, the cost of a single query would be high, and we thus aim at identify the (near)-optimum as efficiently as possible. The whole study is motivated by numerous real scenarios including, but not limited to, clinical trial, A/B testing, advertisement placement optimization. We therefore conclude by some particular focus on one of its most important contributions for the machine learning community, i.e. hyper-parameter optimization.
Complete list of metadata
Contributor : Abes Star :  Contact
Submitted on : Wednesday, January 12, 2022 - 6:50:00 PM
Last modification on : Friday, January 21, 2022 - 3:11:20 AM


Version validated by the jury (STAR)


  • HAL Id : tel-03466525, version 4


Xuedong Shang. Adaptive methods for optimization in stochastic environments. Artificial Intelligence [cs.AI]. Université de Lille, 2021. English. ⟨NNT : 2021LILUB007⟩. ⟨tel-03466525v4⟩



Les métriques sont temporairement indisponibles