Metodebevisregister

Time-MoE

Time-MoE is a billion-scale autoregressive foundation model for universal time-series forecasting, introduced by Shi et al. in 2024 and accepted at ICLR 2025. It combines a decoder-only transformer architecture with sparse Mixture-of-Experts (MoE) feed-forward layers, enabling the model to scale to billions of parameters while activating only a small subset of expert networks per token—dramatically increasing capacity without proportional compute cost.

Sources recorded, not reviewed

Kilderegister

Siteringer kopiert ordrett fra metodens kilderegister. Ingen påstandsnivåverifisering er underforstått fra dem.

Time-MoE (Mixture-of-Experts Time-Series Foundation Model)

Taksonomisk metoderegister · ml-model / deep-learning

Shi, X., Wang, S., Nie, Y., Li, D., Ye, Z., Wen, Q., & Jin, M. (2024). Time-MoE: Billion-scale time series foundation models with mixture of experts. ICLR 2025. · URL

Åpne full metode

Kuraterte påstander

Påstander lagret i bevishovedboken, hver med sin egen vurdering.

Ingen kuraterte påstander ennå

Denne visningen finner ikke opp en påstandsvurdering når hovedboken ikke har noen.

Relaterte metoder

Generert fra metodegrafen og vist som maskinforslåtte relasjoner – ingen bevispåstand er underforstått.

Taxonomic bucketChronosmachine-suggested · Relational suggestion, not evidence.Same method familyMixture of Expertsmachine-suggested · Relational suggestion, not evidence.Taxonomic bucketTimesFMmachine-suggested · Relational suggestion, not evidence.