Levente Kocsis

Levente Kocsis

Auto-generated profile, based on publicly available information

Levente Kocsis

Hungarian Academy of Sciences (MTA SZTAKI)

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 June 2018
Verified
Book Chapter
Closed access
PDF file
ABAndrás Benczúr
András Benczúr
LKLevente Kocsis
Levente Kocsis
RPRóbert Pálovics
Róbert Pálovics

28 March 2006 in Machine Learning
Verified
Journal Article
Closed access
PDF file
LKLevente Kocsis
Levente Kocsis
CSCsaba Szepesvári
Csaba Szepesvári

6 November 2021 in User Modeling and User-Adapted Interaction
Verified
Journal Article
Open access
PDF file
EFErzsébet Frigó
Erzsébet Frigó
LKLevente Kocsis
Levente Kocsis
As a task of high importance for recommender systems, we consider the problem of learning the convex combination of ranking algorithms by online machine learning. First, we propose a stochastic optimization algorithm that uses finite differences. Our new algorithm achieves close to optimal empirical performance for two base rankers, while scaling well with an increased number of models. In our experiments with five real-world recommendation data sets, we show that the combination offers significant improvement over previously known stochastic optimization techniques. The proposed algorithm is the first effective stochastic optimization method for combining ranked recommendation lists by online machine learning. Secondly, we propose an exponentially weighted algorithm based on a grid over the space of combination weights. We show that the algorithm has near-optimal worst-case performance bound. The bound provides the first theoretical guarantee for non-convex bandits using limited number of evaluations under very general conditions.

7 June 2013 in Machine Learning
Verified
Journal Article
Closed access
PDF file
LKLevente Kocsis
Levente Kocsis
AGAndrás György
András György
ABAndrea N. Bán
Andrea N. Bán

16 January 2014 in arXiv
Verified
Preprint
Open access
PDF file
AGAndrás György
András György
LKLevente Kocsis
Levente Kocsis
Local search algorithms applied to optimization problems often suffer from getting trapped in a local optimum. The common solution for this deficiency is to restart the algorithm when no progress is observed. Alternatively, one can start multiple instances of a local search algorithm, and allocate computational resources (in particular, processing time) to the instances depending on their behavior. Hence, a multi-start strategy has to decide (dynamically) when to allocate additional resources to a particular instance and when to start new instances. In this paper we propose multi-start strategies motivated by works on multi-armed bandit problems and Lipschitz optimization with an unknown constant. The strategies continuously estimate the potential performance of each algorithm instance by supposing a convergence rate of the local search algorithm up to an unknown constant, and in every phase allocate resources to those instances that could converge to the optimum for a particular range of the constant. Asymptotic bounds are given on the performance of the strategies. In particular, we prove that at most a quadratic increase in the number of times the target function is evaluated is needed to achieve the performance of a local search algorithm started from the attraction region of the optimum. Experiments are provided using SPSA (Simultaneous Perturbation Stochastic Approximation) and k-means as local search algorithms, and the results indicate that the proposed strategies work well in practice, and, in all cases studied, need only logarithmically more evaluations of the target function as opposed to the theoretically suggested quadratic increase.