Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration
stat.ML, cs.LG, stat.ME
Submitted: 2026-05-11
Updated: 2026-09-26
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Conditional Time Series Forecasting with Convolutional Neural Networks
- Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
- Electricity Price Forecasting: Bridging Linear Models, Neural Networks and Online Learning
- N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
- Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
- Online Conformal Prediction for Non-Exchangeable Panel Data
- Deep Time-Series Forecasting in 10 Years: A Survey