Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Towards Neural Scaling Laws for Time Series Foundation Models
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-537
Moirai's architectural enhancements (any-variate attention, multi-scale patch embedding, diverse mixture distribution) improve in-distribution forecasting but reduce out-of-distribution scalability relative to a simpler encoder-only baseline
IC-538
Chronos-T5's discrete probability prediction approach yields very small power-law exponents on NLL, limiting its scalability, and its in-distribution gains do not extend to out-of-distribution data