no code implementations • 27 Apr 2023 • Cornelius Brand, Robert Ganian, Kirill Simonov
But while the nascent theory of parameterized complexity has allowed us to push beyond the P-NP ``dichotomy'' in classical computational complexity and identify the exact boundaries of tractability for numerous problems, there is no analogue in the domain of sample complexity that could push beyond efficient PAC learnability.
no code implementations • 13 Dec 2021 • Sayan Bandyapadhyay, Fedor V. Fomin, Petr A. Golovach, William Lochet, Nidhi Purohit, Kirill Simonov
(2) For a given set of points, how to find a decision tree with $k$ leaves minimizing the $k$-means/median objective of the resulting explainable clustering?
no code implementations • 19 Oct 2020 • Eduard Eiben, Fedor V. Fomin, Petr A. Golovach, William Lochet, Fahad Panolan, Kirill Simonov
We consider a generalization of the fundamental $k$-means clustering for data with incomplete or corrupted entries.
no code implementations • 20 Jul 2020 • Sayan Bandyapadhyay, Fedor V. Fomin, Kirill Simonov
The new construction allows us to obtain the first coreset for fair clustering in general metric spaces.
no code implementations • 10 May 2019 • Fedor V. Fomin, Petr A. Golovach, Fahad Panolan, Kirill Simonov
Principal component analysis (PCA) is one of the most fundamental procedures in exploratory data analysis and is the basic step in applications ranging from quantitative finance and bioinformatics to image analysis and neuroscience.