Alexander Korotin

TL;DR: This paper proposes a novel end-to-end algorithm for training generative models which uses a non-minimax objective simplifying model training and uses the approximation of Wasserstein-2 distance by Input Convex Neural Networks.

TL;DR: A comparative study of the players' and professional players’ (athletes’) performance in Counter Strike: Global Offensive discipline is presented, based on ubiquitous sensing helping identify the biometric features significantly contributing to the classification of particular skills of thePlayers.

TL;DR: A novel neural-networks-based algorithm to compute optimal transport maps and plans for strong and weak transport costs is presented and it is proved that they are universal approximators of transport plans between probability distributions.

Abstract: One possible approach to tackle the class imbalance in classification tasks is to resample a training dataset, i.e., to drop some of its elements or to synthesize new ones. There exist several widely-used resampling methods. Recent research showed that the choice of resampling method significantly affects the quality of classification, which raises the resampling selection problem. Exhaustive search for optimal resampling is time-consuming and hence it is of limited use. In this paper, we describe an alternative approach to the resampling selection. We follow the meta-learning concept to build resampling recommendation systems, i.e., algorithms recommending resampling for datasets on the basis of their properties.

TL;DR: This paper follows the meta-learning concept to build resampling recommendation systems, i.e., algorithms recommending resampled for datasets on the basis of their properties.