non-stationarity
Non-stationarity refers to situations where the underlying data distribution changes over time or across different environments. This poses challenges for AI models, which may need to adapt continually to maintain performance.
- AdaTS: Learning Adaptive Time Series Representations via Dynamic Soft Contrasts
- Flow based approach for Dynamic Temporal Causal models with non-Gaussian or Heteroscedastic Noises
- Forecasting in Offline Reinforcement Learning for Non-stationary Environments
- Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting
- Meta Guidance: Incorporating Inductive Biases into Deep Time Series Imputers
- Non-stationary Equivariant Graph Neural Networks for Physical Dynamics Simulation
- PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation
- R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
- Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning