10 papers
PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection
Mateusz Smendowski, Kamil Faber, Piotr Nawrocki +2
Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices…
Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios
Kamil Faber, Mateusz Smendowski, Roberto Corizzo
Continual anomaly detection (CAD) studies how models can adapt to evolving data distributions while retaining performance on previously observed regimes. CAD benchmarks, however, d…
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
Katarzyna Filus, Kamil Faber, Roberto Corizzo +1
Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catas…
Goal-Conditioned Decision Transformer for Multi-Goal Offline Reinforcement Learning
PaweŠGajewski, Dominik Żurek, Marcin PietroŠ+1
Reinforcement learning (RL) in robotics faces significant hurdles regarding sample efficiency and generalization across varying goals. While Offline RL mitigates the need for costl…
TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning
Dominik Żurek, Kamil Faber, Marcin Pietron +2
Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This s…
Rethinking the Harmonic Loss via Non-Euclidean Distance Layers
Maxwell Miller-Golub, Collin Coil, Kamil Faber +4
Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencie…