BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:ECAS-ENBIS Course: Adaptive Machine Learning for Time Series Forec
 asting
DTSTART:20260906T114500Z
DTEND:20260906T154500Z
DTSTAMP:20260809T074300Z
UID:indico-event-86@conferences.enbis.org
DESCRIPTION:\nECAS-ENBIS Course:  Adaptive Machine Learning for Time Seri
 es Forecasting\nPart of the ENBIS-26 Florence conference.\nThis half-day c
 ourse is a joint initiative from ENBIS and ECAS (http://ecas.fenstats.eu/)
  which has provided courses since 1987 to achieve training in special area
 s of statistics for both researchers and teachers for universities and pro
 fessionals in industry fields.\nInstructor\nYannig Goude (EDF\, France)\nO
 verview\nThis course focuses on adaptive machine learning tools for time s
 eries forecasting. Drawing on research developed at EDF R&D\, we will cove
 r interpretable machine learning methods\, such as Generalized Additive Mo
 dels (GAMs) and Kalman-filtered GAMs\, designed to adapt to non-stationary
  contexts (e.g.\, data drift\, structural breaks). The second part of the 
 course explores modern approaches\, including foundation models for time s
 eries and tabular data\, as well as online expert aggregation methods.\nWe
  will discuss the theoretical foundations of these methods alongside pract
 ical examples (R and Python notebooks) using the following packages:\n• 
 mgcv (GAMs)\n• qgam (Quantile GAMs)\n• viking (State-Space Models Infe
 rence by Kalman or Viking)\n• opera (Online Prediction by Expert Aggrega
 tion)\n\n• pytabkit\n \n\n\nWe will illustrate these methods using real
 -world datasets (electricity demand\, renewable production\, electricity p
 rices). These datasets provide excellent examples of time-varying environm
 ents\, reflecting longer-term changes in consumption habits and the increa
 sing penetration of intermittent power generation.\nThis 4-hour applicativ
 e course will include about 1 hour of hands-on practice (notebook presenta
 tion).\n\n \n \nShort bio\nYannig Goude is a Senior Researcher at EDF R&
 D and an Associate Professor in the Mathematics Department at Université 
 Paris-Saclay (France) where he currently teaches courses on machine learni
 ng and time series analysis. At EDF R&D\, he works at the OSIRIS departmen
 t (Optimization\, Simulation\, Risk\, and Statistics). His research center
 s on statistical methods and machine learning for the energy sector\, with
  specific interests in:\n• Time series forecasting\n• Generalized Addi
 tive Models (GAMs)\n• Aggregation of Experts\n• Application on energy 
 mangement\n \nHe has authored numerous papers in leading journals such as
  IEEE Transactions on Smart Grid and the Journal of the Royal Statistical 
 Society\, JASA\, NeurIPS\, ICML..\n\n Bibliography \n• Antoniadis\, A.
 \, Cugliari\, J.\, Fasiolo\, M.\, Goude\, Y.\, & Poggi\, J. M. (2024). St
 atistical Learning Tools for Electricity Load Forecasting. Springer Intern
 ational Publishing AG.\n• Gaillard\, P.\, Goude\, Y.\, & Nedellec\, R. (
 2016). Additive models and robust aggregation for GEFCom2014 probabilistic
  electric load and electricity price forecasting. International Journal o
 f forecasting\, 32(3)\, 1038-1050.\n• Fasiolo\, M.\, Wood\, S. N.\, Zaf
 fran\, M.\, Nedellec\, R.\, & Goude\, Y. (2021). Fast calibrated additive 
 quantile regression. Journal of the American Statistical Association\, 1
 16(535)\, 1402-1412.\n• De Vilmarest\, J.\, & Goude\, Y. (2022). State-s
 pace models for online post-covid electricity load forecasting competition
 . IEEE Open Access Journal of Power and Energy\, 9\, 192-201.\n• Wood\
 , S. N. (2017). Generalized additive models: an introduction with R. chap
 man and hall/CRC.\n• Cesa-Bianchi\, N.\, & Lugosi\, G. (2006). Predicti
 on\, learning\, and games. Cambridge university press.\n• Holzmüller\, 
 D.\, Grinsztajn\, L.\, & Steinwart\, I. (2024). Better by default: Strong 
 pre-tuned mlps and boosted trees on tabular data. Advances in Neural Info
 rmation Processing Systems\, 37\, 26577-26658.\n \n \n\nhttps://confere
 nces.enbis.org/event/86/
URL:https://conferences.enbis.org/event/86/
END:VEVENT
END:VCALENDAR