When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting
cs.LG
Submitted: 2026-09-01
Updated: 2026-09-01
Code: https://github.com/keiotakmin/tsf-edge-adaptation
Terminology
Sources
- Act Now: A Novel Online Forecasting Framework for Large-Scale Streaming Data
- Towards Principled Test-Time Adaptation for Time Series Forecasting
- Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adapt
- On-Device Training of PV Power Forecasting Models in a Smart Meter for Grid Edge Intelligence
- Adapt Only When It Pays: Budgeted Decision-Loss Priority for Delayed Online Time-Series Adaptation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks