PhD student at University of Warsaw,
Institute of Mathematics
b.polaczykat@mimuw.edu.pl
office #4500
arXiv ◌
Scholar ◌
ORCID ◌
GitHub
My supervisor is Radosław Adamczak.
B. Polaczyk, J. Cyranka,
Improved overparametrization bounds for global convergence of stochastic gradient descent for shallow neural networks,
preprint;
R. Adamczak, B. Polaczyk,
Concentration inequalities for some negatively dependent binary random variables,
preprint;
R. Adamczak, B. Polaczyk, M. Strzelecki,
Modified log-Sobolev inequalities, Beckner inequalities and moment estimates,
J. Funct. Anal. 282 (2022), no. 7, 109349.
[talk;
slides];
B. Polaczyk,
Concentration of the empirical spectral distribution of random
matrices with dependent entries,
Electron. Commun. Probab. 24 (2019), no. 78, 1-15.;
R. Adamczak, M. Kotowski, B. Polaczyk, M. Strzelecki,
A note on concentration for polynomials in the Ising model,
Electron. J. Probab. 24 (2019), no. 42, 1-22.;
None :-)
Currently, I'm a research assistant at Foundations of Interpretable and Reliable Machine Learning NAWA project and an investigator in Concentration of measure and functional inequalities NCN project.
Here you can find notes that I have taken during Nathael Gozlan's lectures on Optimal transport and concentration of measure at Warsaw Summer School in Probability 2017 and here - a poster about my MSc thesis.
A novel proof of the Riemann hypothesis.