Najnowsze publikacje

• Changlong Wu, Jin Sima, Wojciech Szpankowski, Certifying Capabilities from Finite Tests: When Is It Possible?, International Conference on Machine Learning [ICML], (2026),
• Michael Drmota, Philippe Jacquet, Changlong Wu, Wojciech Szpankowski, Phase Transition of Regret for Logistic Regression with Large Weights, Algorithmic Learning Theory [ALT], (2026),
• Mohsen Heidari, Masih Mozakka, Wojciech Szpankowski, Hadamard Test is Sufficient for Efficient Quantum Gradient Estimation with Lie Algebraic Symmetries, Advances in Neural Information Processing Systems [NeurIPS], (2025),
• Pramith Devulapalli, Changlong Wu, Ananth Grama, Wojciech Szpankowski, Agnostic Continuous-Time Online Learning, Advances in Neural Information Processing Systems [NeurIPS], (2025),
• Changlong Wu, Ananth Grama, Wojciech Szpankowski, No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models, International Conference on Learning Representations [ICLR], (2025),