collaborators

6 papers

math.OC2024

Reduced-Rank Estimation for Ill-Conditioned Stochastic Linear Model with High Signal-to-Noise Ratio

Tomasz Piotrowski, Isao Yamada

Reduced-rank approach has been used for decades in robust linear estimation of both deterministic and random vector of parameters in linear model y=Hx+\sqrt{epsilon}n. In practical…

stat.AP2024

Performance of the stochastic MV-PURE estimator in highly noisy settings

Tomasz Piotrowski, Isao Yamada

The stochastic minimum-variance pseudo-unbiased reduced-rank estimator (stochastic MV-PURE estimator) has been developed to provide linear estimation with robustness against high n…

eess.SP2024

Localization of Brain Activity from EEG/MEG Using MV-PURE Framework

Tomasz Piotrowski, Jan Nikadon, Alexander Moiseev

We consider the problem of localization of sources of brain electrical activity from electroencephalographic (EEG) and magnetoencephalographic (MEG) measurements using spatial filt…

eess.SP2024

MV-PURE Spatial Filters with Application to EEG/MEG Source Reconstruction

Tomasz Piotrowski, Jan Nikadon, David Gutierrez

In this paper we propose spatial filters for a linear regression model which are based on the minimum-variance pseudo-unbiased reduced-rank estimation (MV-PURE) framework. As a sam…

stat.ML2024

Fixed points of nonnegative neural networks

Tomasz J. Piotrowski, Renato L. G. Cavalcante, Mateusz Gabor

We use fixed point theory to analyze nonnegative neural networks, which we define as neural networks that map nonnegative vectors to nonnegative vectors. We first show that nonnega…

stat.ML2024

Inverse Feasibility in Over-the-Air Federated Learning

Tomasz Piotrowski, Rafail Ismayilov, Matthias Frey +1

We introduce the concept of inverse feasibility for linear forward models as a tool to enhance OTA FL algorithms. Inverse feasibility is defined as an upper bound on the condition…