Online Curvature-Aware Replay: Leveraging $\mathbf{2^{nd}}$ Order Information for Online Continual Learning

Documenti analoghi

• Online Continual Learning for Time Series: a Natural Score-driven Approach
  di: Urettini, Edoardo, et al.
  Pubblicazione: (2026)
• Unbiased Online Curvature Approximation for Regularized Graph Continual Learning
  di: Yin, Jie, et al.
  Pubblicazione: (2025)
• Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning
  di: Song, Chihyeon, et al.
  Pubblicazione: (2025)
• GAS-Norm: Score-Driven Adaptive Normalization for Non-Stationary Time Series Forecasting in Deep Learning
  di: Urettini, Edoardo, et al.
  Pubblicazione: (2024)
• How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning
  di: Serra, Giuseppe, et al.
  Pubblicazione: (2024)