Copertina

Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mahtout, Btissame El, Ziel, Florian
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Methodology
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Electricity Price Forecasting: Bridging Linear Models, Neural Networks and Online Learning
di: Mahtout, Btissame El, et al.
Pubblicazione: (2026)

Varying-Coefficient Mixture of Experts Model
di: Zhao, Qicheng, et al.
Pubblicazione: (2026)

Identification and Estimation under Multiple Versions of Treatment: Mixture-of-Experts Approach
di: Yoshikawa, Kohei, et al.
Pubblicazione: (2026)

Online Distributional Regression
di: Hirsch, Simon, et al.
Pubblicazione: (2024)

Incorporating Expert Knowledge into Bayesian Causal Discovery of Mixtures of Directed Acyclic Graphs
di: Björkman, Zachris, et al.
Pubblicazione: (2025)

Fast Model Selection and Stable Optimization for Softmax-Gated Multinomial-Logistic Mixture of Experts Models
di: Tran, TrungKhang, et al.
Pubblicazione: (2026)

Wavelet Mixture of Experts for Time Series Forecasting
di: Zhou, Zheng, et al.
Pubblicazione: (2025)

Autoregressive with Slack Time Series Model for Forecasting a Partially-Observed Dynamical Time Series
di: Okuno, Akifumi, et al.
Pubblicazione: (2023)

Improving Forecasts for Heterogeneous Time Series by "Averaging", with Application to Food Demand Forecast
di: Neubauer, Lukas, et al.
Pubblicazione: (2023)

ProbRes: Volatility Learning for Probabilistic Time-Series Forecasting
di: Wang, Tingting, et al.
Pubblicazione: (2026)

Sliding-Window Signatures for Time Series: Application to Electricity Demand Forecasting
di: Drobac, Nina, et al.
Pubblicazione: (2025)

Revisiting Incremental Stochastic Majorization-Minimization Algorithms with Applications to Mixture of Experts
di: Tran, TrungKhang, et al.
Pubblicazione: (2026)

A Gentle Introduction to Conformal Time Series Forecasting
di: Stocker, M., et al.
Pubblicazione: (2025)

Model Selection for Gaussian-gated Gaussian Mixture of Experts Using Dendrograms of Mixing Measures
di: Thai, Tuan, et al.
Pubblicazione: (2025)

SPINEX-TimeSeries: Similarity-based Predictions with Explainable Neighbors Exploration for Time Series and Forecasting Problems
di: Naser, Ahmed Z, et al.
Pubblicazione: (2024)

Crowdsourcing Without People: Modelling Clustering Algorithms as Experts
di: Lorentz, Jordyn E. A., et al.
Pubblicazione: (2025)

Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity
di: Kamarthi, Harshavardhan, et al.
Pubblicazione: (2024)

M$^3$TN: Multi-gate Mixture-of-Experts based Multi-valued Treatment Network for Uplift Modeling
di: Sun, Zexu, et al.
Pubblicazione: (2024)

Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency without Model Sweeps
di: Hai, Do Tien, et al.
Pubblicazione: (2025)

DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series
di: Wu, Dongze, et al.
Pubblicazione: (2025)

Time Tracker: Mixture-of-Experts-Enhanced Foundation Time Series Forecasting Model with Decoupled Training Pipelines
di: Liang, Aobo, et al.
Pubblicazione: (2025)

Forecasting Multivariate Time Series under Predictive Heterogeneity: A Validation-Driven Clustering Framework
di: Ma, Ziling, et al.
Pubblicazione: (2026)

AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
di: Wang, Rui, et al.
Pubblicazione: (2026)

Mixture-of-Linear-Experts for Long-term Time Series Forecasting
di: Ni, Ronghao, et al.
Pubblicazione: (2023)

Counterfactual Probabilistic Diffusion with Expert Models
di: Mu, Wenhao, et al.
Pubblicazione: (2025)

Expert-elicitation method for non-parametric joint priors using normalizing flows
di: Bockting, Florence, et al.
Pubblicazione: (2024)

Towards Complete Causal Explanation with Expert Knowledge
di: Venkateswaran, Aparajithan, et al.
Pubblicazione: (2024)

COKE: Causal Discovery with Chronological Order and Expert Knowledge in High Proportion of Missing Manufacturing Data
di: Ou, Ting-Yun, et al.
Pubblicazione: (2024)

Automatic Change-Point Detection in Time Series via Deep Learning
di: Li, Jie, et al.
Pubblicazione: (2022)

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
di: Lv, Ang, et al.
Pubblicazione: (2025)

TimeExpert: Boosting Long Time Series Forecasting with Temporal Mix of Experts
di: Ma, Xiaowen, et al.
Pubblicazione: (2025)

Continual Traffic Forecasting via Mixture of Experts
di: Lee, Sanghyun, et al.
Pubblicazione: (2024)

Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
di: Nochumsohn, Liran, et al.
Pubblicazione: (2025)

MoHETS: Long-term Time Series Forecasting with Mixture-of-Heterogeneous-Experts
di: Ortigossa, Evandro S., et al.
Pubblicazione: (2026)

Interpreting Time Series Forecasts with LIME and SHAP: A Case Study on the Air Passengers Dataset
di: Shukla, Manish
Pubblicazione: (2025)

MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models
di: Liu, Yiwen, et al.
Pubblicazione: (2025)

Estimating Item Difficulty with Large Language Models as Experts
di: Kolesnikova, Diana, et al.
Pubblicazione: (2026)

Time Series Gaussian Chain Graph Models
di: Fang, Qin, et al.
Pubblicazione: (2026)

Why Model Selection Fails in Time Series Forecasting: An Empirical Study of Instability Across Data Regimes
di: Akinci, Tahir Cetin, et al.
Pubblicazione: (2026)

Causal Inference with Categorical Unobserved Confounder via Mixture Learning
di: Saha, Aytijhya, et al.
Pubblicazione: (2026)