3 papers
cs.LG2026
Online Continual Learning for Time Series: a Natural Score-driven Approach
Edoardo Urettini, Daniele Atzeni, Ioanna-Yvonni Tsaknaki +1
Online continual learning (OCL) methods adapt to changing environments without forgetting past knowledge. Similarly, online time series forecasting (OTSF) is a real-world problem w…
cs.LG2025
Online Curvature-Aware Replay: Leveraging Order Information for Online Continual Learning
Edoardo Urettini, Antonio Carta
Online Continual Learning (OCL) models continuously adapt to nonstationary data streams, usually without task information. These settings are complex and many traditional CL method…
cs.LG2024
GAS-Norm: Score-Driven Adaptive Normalization for Non-Stationary Time Series Forecasting in Deep Learning
Edoardo Urettini, Daniele Atzeni, Reshawn J. Ramjattan +1
Despite their popularity, deep neural networks (DNNs) applied to time series forecasting often fail to beat simpler statistical models. One of the main causes of this suboptimal pe…