Wojciech Kotłowski


My research area is machine learning. I am mainly interested in online learning and sequential prediction, but I also work
on other theoretical aspects of learning from data.
I am a faculty member at
the Institute of Computing Science, Poznań University of Technology.
In 2018, I received a habilitation degree in Computer Science.
In 20092012, I was a postdoctoral fellow at Centrum Wiskunde & Informatica (CWI), in the group of Peter Grünwald. I received my Ph.D. in Computer Science (2009) from Poznań University of Technology under supervision of prof. Roman Słowiński.
More information in my CV.
Some recent publications (see all)

Comparison of machine learning algorithms used to classify the asteroids observed by allsky surveys
H. Klimczak, D. Oszkiewicz, B. Carry, A. Penttilä, W. Kotlowski, A. Kryszczyńska, E. Wilawer
Astronomy & Astrophysics, 2022

Robust online convex optimization in the presence of outliers
Tim van Erven, Sarah Sachs, Wouter M. Koolen, Wojciech Kotłowski
Conference on Learning Theory (COLT), 2021

A case where a spindly twolayer linear network decisively outperforms any neural network with a fully connected input layer
Manfred K. Warmuth, Wojciech Kotłowski, Ehsan Amid
Algorithmic Learning Theory (ALT), 2021

Learning to crawl
Utkarsh Upadhyay, Róbert BusaFekete, Wojciech Kotłowski, Dávid Pál, Balázs Szörényi
AAAI Conference on Artificial Intelligence, 2020

Scaleinvariant unconstrained online learning
Wojciech Kotłowski
Theoretical Computer Science, 2020

Bandit Principal Component Analysis
Wojciech Kotłowski, Gergely Neu
Conference on Learning Theory (COLT), 2019

Adaptive scaleinvariant online algorithms for learning linear models
Michał Kempka, Wojciech Kotłowski, Manfred K. Warmuth
International Conference on Machine Learning (ICML), 2019

On minimaxity of Follow the Leader strategy
in the stochastic setting
Wojciech Kotłowski
Theoretical Computer Science, 2018

The Many Faces of Exponential Weights in Online Learning
Dirk van der Hoeven, Tim van Erven, Wojciech Kotłowski
Conference on Learning Theory (COLT), 2018

Random Permutation Online Isotonic Regression
Wojciech Kotłowski, Wouter Koolen, Alan Malek
Neural Information Processing Systems (NIPS), 2017

Consistency Analysis for Binary Classification Revisited
Krzysztof Dembczyński, Wojciech Kotłowski, Oluwasanmi Koyejo, Nagarajan Natarajan
International Conference on Machine Learning (ICML), 2017

Surrogate regret bounds for
generalized classification performance metrics
Wojciech Kotłowski, Krzysztof Dembczyński
Machine Learning, 2017