Wojciech Szpankowski
Computer Science · Purdue University West Lafayette
Publications
441
Citations
6,728
Est. group size
~3
Recurring co-author estimate
Active years
46
Publishing since 1981
Wojciech Szpankowski works in information theory and theoretical computer science, focusing on how to precisely measure the complexity and compressibility of data and how to design algorithms that learn or make predictions with provable guarantees. Recent work centers on online learning (algorithms that update predictions as new data arrives), minimax regret analysis (bounding worst-case prediction error), data compression methods, and mathematical models of random graphs such as duplication-divergence network models used to describe biological or social networks.
Publication output rose through the late 2010s and peaked around 2020-2021, then became more variable and lower in the most recent years (2023-2026), suggesting a slowing pace after a period of steady, higher activity.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Online universal learning from information-theoretic perspective
Foundations and Trends® in Communications and Information Theory · 2026
- Precise Regularized Minimax Regret With Unbounded Weights
IEEE Transactions on Information Theory · 2025
- Online Learning with Nasty Experts
2025
- Oracle-Efficient Hybrid Online Learning with Unknown Distribution
arXiv (Cornell University) · 2024
- Online Distribution Learning with Local Private Constraints
arXiv (Cornell University) · 2024
- On the Concentration of the Maximum Degree in the Duplication-Divergence Models
SIAM Journal on Discrete Mathematics · 2024
- Minimax Regret with Unbounded Weights
2024
- Low Complexity Approximate Bayesian Logistic Regression for Sparse Online Learning
2024
- Study of Lempel-Ziv'78 for Markov Sources: From incomplete to full analysis
HAL (Le Centre pour la Communication Scientifique Directe) · 2024
- Breaking through the classical Shannon entropy limit: A new frontier through logical semantics
arXiv (Cornell University) · 2024
- Analytic Information Theory
Cambridge University Press eBooks · 2023
- On the concentration of the maximum degree in the duplication-divergence models
arXiv (Cornell University) · 2023
- Precise Minimax Regret for Logistic Regression
2022 IEEE International Symposium on Information Theory (ISIT) · 2022
- Sequential universal modeling for non-binary sequences with constrained distributions
Communications in Information and Systems · 2022
- Precise Minimax Regret for Logistic Regression
HAL (Le Centre pour la Communication Scientifique Directe) · 2022
- arXiv (Cornell University)×34
- IEEE Transactions on Information Theory×6
- HAL (Le Centre pour la Communication Scientifique Directe)×4
- IEEE Transactions on Molecular Biological and Multi-Scale Communications×2
- Algorithmica×2
- Mark Daniel Ward
Computer Science · Purdue University West Lafayette
- Minshen Zhu
Computer Science · Purdue University West Lafayette
- M. Oğuzhan Külekçi
Computer Science · Indiana University
- Cynthia A. Brown
Computer Science · Indiana University
- Funda Ergün
Computer Science · Indiana University
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile