6 papers · 1 filter
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…
Correcting Performance Estimation Bias in Imbalanced Classification with Minority Subconcepts
Taylor Maxson, Roberto Corizzo, Yaning Wu +2
Class-level evaluation can conceal substantial performance disparities across subconcepts within the same class, causing models that perform well on average to fail on specific sub…
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…
xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection
Kamil Faber, Marcin PietroÅ, Dominik Å»urek +1
The recently proposed xLSTM is a powerful model that leverages expressive multiplicative gating and residual connections, providing the temporal capacity needed for long-horizon fo…
TinySubNets: An efficient and low capacity continual learning strategy
Marcin PietroÅ, Kamil Faber, Dominik Å»urek +1
Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effe…