Papers
- Learning to Forget: Continual Learning with Adaptive Weight Decay
A. A. Ramesh, A. Lewandowski, J. Schmidhuber
Under Review, 2026 - Mind the gap between programming in natural language and in formal languages
A. Lewandowski, H. Dai, F. Zanini, M. C. Machado, D. Schuurmans
Under Review, 2026
Note: this is a journal submission combining 2601.08061 and 2410.03170 - The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis
A. Lewandowski, A. A. Ramesh, E. Meyer, D. Schuurmans, M. C. Machado
Neural Information Processing Systems (NeurIPS), 2025
(Spotlight)
Earlier version: RLDM 2025 (with S. Kumar) - A Unified Noise-Curvature View of Loss of Trainability
G. S. Baveja, A. Lewandowski, M. Schmidt
Workshop on Optimization for Machine Learning at NeurIPS, 2025 - Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning
R. Surdej, M. Bortkiewicz, A. Lewandowski, M. Ostaszewski, C. Lyle
Conference on Lifelong Learning Agents (CoLLAs), 2025
(Oral Presentation) - Plastic Learning with Deep Fourier Features
A. Lewandowski, D. Schuurmans, M. C. Machado
International Conference on Learning Representations (ICLR), 2025 - Learning Continually by Spectral Regularization
A. Lewandowski, M. Bortkiewicz, S. Kumar, A. György, D. Schuurmans, M. Ostaszewski, M. C. Machado
International Conference on Learning Representations (ICLR), 2025 - The Need for a Big World Simulator: A Scientific Challenge for Continual Learning
S. Kumar, H. J. Jeon, A. Lewandowski, B. van Roy
Finding the Frame Workshop at RLC, 2024
(Oral Presentation) - Directions of Curvature as an Explanation for Loss of Plasticity
A. Lewandowski, H. Tanaka, D. Schuurmans, M. C. Machado
CoRR, abs/2312.00246v2, 2023 - Reinforcement Teaching
C. Muslimani*, A. Lewandowski*, D. Schuurmans, M. E. Taylor, J. Luo
Transactions on Machine Learning Research (TMLR), 2023
*Equal contribution
© Alex Lewandowski. Last modified: May 07, 2026. Website built with Franklin.jl and the Julia programming language.