Daniel Schmidt (Monash University):  Fundamental limitations of foundational time series forecasting models: The need for multimodality and rigorous evaluation

Time and place:
June 2nd, 14:15
Lecture room T5, CS Buidling, Aalto University (in person) and Zoom

Abstract: In this talk, we will discuss some fundamental limitations we perceive in the current operation of foundational models in the context of time series forecasting. We’ll argue that training on ever more data is not always beneficial, and we'll illustrate how common yet often inadequate evaluation practices can obscure these limitations. Ultimately, we will argue that the way to address these challenges is through multimodality.

Speaker:  Daniel Schmidt is an Associate Professor of Computer Science at the Department of Data Science and AI, Monash University, Australia. He obtained his PhD in the area of information theoretic statistical inference in 2008 from Monash University. From 2009 to 2018 he was employed at the University of Melbourne, working in the field of statistical genomics (GWAS, epigenetics and cancer). Since 2018 he has been employed at Monash University in a teaching and research position. His research interests are primarily time series classification and forecasting, Bayesian inference and MCMC, Bayesian optimisation and function approximation. He also has a keen interest in the best ways to provide statistical/machine learning education.