non-stationary data
Non-stationary data refers to data where statistical properties change over time, posing challenges in learning algorithms that assume stationary conditions, necessitating adaptive approaches.
- Continual Gaussian Mixture Distribution Modeling for Class Incremental Semantic Segmentation
- Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data
- Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction
- REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning
- STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data