Vladimir Kostic

According to our database, Vladimir Kostic authored at least 42 papers between 2006 and 2024.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of four.

2024

Neural Conditional Probability for Inference.

Vladimir R. Kostic, Karim Lounici, Grégoire Pacreau, Pietro Novelli, Giacomo Turri, Massimiliano Pontil

CoRR, 2024

From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach.

Timothee Devergne, Vladimir Kostic, Michele Parrinello, Massimiliano Pontil

CoRR, 2024

Learning the Infinitesimal Generator of Stochastic Diffusion Processes.

Vladimir R. Kostic, Karim Lounici, Hélène Halconruy, Timothee Devergne, Massimiliano Pontil

CoRR, 2024

Morphological Symmetries in Robotics.

Daniel Felipe Ordoñez Apraez, Giulio Turrisi, Vladimir Kostic, Mario Martín, Antonio Agudo, Francesc Moreno-Noguer, Massimiliano Pontil, Claudio Semini, Carlos Mastalli

CoRR, 2024

Dynamics harmonic analysis of robotic systems: Application in data-driven Koopman modelling.

Daniel Felipe Ordoñez Apraez, Vladimir Kostic, Giulio Turrisi, Pietro Novelli, Carlos Mastalli, Claudio Semini, Massimiliano Pontil

Proceedings of the 6th Annual Learning for Dynamics & Control Conference, 2024

Consistent Long-Term Forecasting of Ergodic Dynamical Systems.

Vladimir R. Kostic, Karim Lounici, Prune Inzerilli, Pietro Novelli, Massimiliano Pontil

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Learning invariant representations of time-homogeneous stochastic dynamical systems.

Vladimir R. Kostic, Pietro Novelli, Riccardo Grazzi, Karim Lounici, Massimiliano Pontil

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Correlation-Comparison Analysis as a New Way of Data-Mining: Application to Neural Data.

Ivan Grbatinic, Bojana Krstonosic, Dragana Srebro, Nemanja Puric, Marija Dubak, Vladan Dusanic, Vladimir Kostic, Nebojsa T. Milosevic

SN Comput. Sci., September, 2023

The method of randomized Bregman projections for stochastic feasibility problems.

Vladimir R. Kostic, Saverio Salzo

Numer. Algorithms, July, 2023

A randomized algorithm to solve reduced rank operator regression.

Giacomo Turri, Vladimir Kostic, Pietro Novelli, Massimiliano Pontil

CoRR, 2023

Deep projection networks for learning time-homogeneous dynamical systems.

Vladimir R. Kostic, Pietro Novelli, Riccardo Grazzi, Karim Lounici, Massimiliano Pontil

CoRR, 2023

Koopman Operator Learning: Sharp Spectral Rates and Spurious Eigenvalues.

Vladimir Kostic, Karim Lounici, Pietro Novelli, Massimiliano Pontil

CoRR, 2023

Estimating Koopman operators with sketching to provably learn large scale dynamical systems.

Giacomo Meanti, Antoine Chatalic, Vladimir Kostic, Pietro Novelli, Massimiliano Pontil, Lorenzo Rosasco

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Sharp Spectral Rates for Koopman Operator Learning.

Vladimir Kostic, Karim Lounici, Pietro Novelli, Massimiliano Pontil

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Evaluation of vibrodiagnostic optimization model for turbo pumps.

Milos Milovancevic, Nebojsa Denic, Ljubomir Vracar, Nenad Kojic, Vladimir Kostic, Srecko Bacevac

Adv. Eng. Softw., 2022

Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces.

Vladimir Kostic, Pietro Novelli, Andreas Maurer, Carlo Ciliberto, Lorenzo Rosasco, Massimiliano Pontil

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Batch Greenkhorn Algorithm for Entropic-Regularized Multimarginal Optimal Transport: Linear Rate of Convergence and Iteration Complexity.

Vladimir R. Kostic, Saverio Salzo, Massimiliano Pontil

Proceedings of the International Conference on Machine Learning, 2022

2021

From pseudospectra of diagonal blocks to pseudospectrum of a full matrix.

Vladimir R. Kostic, Ljiljana Cvetkovic, Ernest Sanca

J. Comput. Appl. Math., 2021

Convergence of Batch Greenkhorn for Regularized Multimarginal Optimal Transport.

Vladimir Kostic, Saverio Salzo, Massimiliano Pontil

CoRR, 2021

2019

New pseudospectra localizations with application in ecology and vibration analysis.

Dragana Lj. Cvetkovic, Ljiljana Cvetkovic, Vladimir R. Kostic

Proceedings of the IEEE 9th Annual Computing and Communication Workshop and Conference, 2019

2018

On the Geršgorin-type localizations for nonlinear eigenvalue problems.

Vladimir Kostic, Dragana Gardasevic

Appl. Math. Comput., 2018

2017

On the inertia of the block H-matrices.

Vladimir Kostic, Ljiljana Cvetkovic

Numer. Linear Algebra Appl., 2017

2016

An algorithm for computing minimal Geršgorin sets.

Vladimir R. Kostic, Agnieszka Miedlar, Ljiljana Cvetkovic

Numer. Linear Algebra Appl., 2016

Pseudospectra localizations and their applications.

Vladimir R. Kostic, Ljiljana Cvetkovic, Dragana Lj. Cvetkovic

Numer. Linear Algebra Appl., 2016

A wider convergence area for the MSTMAOR iteration methods for LCP.

Ljiljana Cvetkovic, Vladimir Kostic, Ernest Sanca

Numer. Algorithms, 2016

Euclidean norm estimates of the inverse of some special block matrices.

Ljiljana Cvetkovic, Vladimir Kostic, Ksenija Doroslovacki, Dragana Lj. Cvetkovic

Appl. Math. Comput., 2016

2015

On Matrix Nearness Problems: Distance to Delocalization.

Vladimir R. Kostic, Agnieszka Miedlar, Jeroen J. Stolwijk

SIAM J. Matrix Anal. Appl., 2015

Stability analysis of turbulent heat exchange over the heterogeneous environmental interface in climate models.

Dragutin T. Mihailovic, Vladimir Kostic, Gordan Mimic, Ljiljana Cvetkovic

Appl. Math. Comput., 2015

On general principles of eigenvalue localizations via diagonal dominance.

Vladimir Kostic

Adv. Comput. Math., 2015

2014

A note on the convergence of the MSMAOR method for linear complementarity problems.

Ljiljana Cvetkovic, Vladimir Kostic

Numer. Linear Algebra Appl., 2014

On the choice of parameters in MAOR type splitting methods for the linear complementarity problem.

Ljiljana Cvetkovic, Apostolos Hadjidimos, Vladimir Kostic

Numer. Algorithms, 2014

Spectrum localizations for matrix operators on I^P spaces.

J. Aleksic, Vladimir Kostic, Milica Zigic

Appl. Math. Comput., 2014

2012

Localization of generalized eigenvalues by Cartesian ovals.

Vladimir Kostic, Richard S. Varga, Ljiljana Cvetkovic

Numer. Linear Algebra Appl., 2012

Max-norm bounds for the inverse of S-Nekrasov matrices.

Ljiljana Cvetkovic, Vladimir Kostic, Ksenija Doroslovacki

Appl. Math. Comput., 2012

Application of generalized diagonal dominance in wireless sensor network optimization problems.

Ljiljana Cvetkovic, Vladimir Kostic

Appl. Math. Comput., 2012

2011

Eigenvalue Localization Refinements for Matrices Related to Positivity.

Ljiljana Cvetkovic, Vladimir Kostic, Juan Manuel Peña

SIAM J. Matrix Anal. Appl., 2011

A simple generalization of Geršgorin's theorem.

Ljiljana Cvetkovic, Vladimir Kostic, Rafael Bru, Francisco Pedroche

Adv. Comput. Math., 2011

2009

Geršgorin-type localizations of generalized eigenvalues.

Vladimir Kostic, Ljiljana Cvetkovic, Richard S. Varga

Numer. Linear Algebra Appl., 2009

A new subclass of H-matrices.

Ljiljana Cvetkovic, Vladimir Kostic, Sonja Rauski

Appl. Math. Comput., 2009

2008

Further results on H-matrices and their Schur complements.

Ljiljana Cvetkovic, Vladimir Kostic, Maja Kovacevic, Tomasz Szulc

Appl. Math. Comput., 2008

2007

A note on the convergence of the AOR method.

Ljiljana Cvetkovic, Vladimir Kostic

Appl. Math. Comput., 2007

2006

New subclasses of block <i>H</i>-matrices with applications to parallel decomposition-type relaxation methods.

Ljiljana Cvetkovic, Vladimir Kostic

Numer. Algorithms, 2006