6 papers · 1 filter
Adapting Time Series Foundation Models through Data Mixtures
Thomas L. Lee, Edoardo M. Ponti, Amos Storkey
Time series foundation models (TSFMs) have become increasingly popular for zero-shot forecasting. However, for a new time series domain not fully covered by the pretraining set, pe…
Signature-Kernel Based Evaluation Metrics for Robust Probabilistic and Tail-Event Forecasting
Benjamin R. Redhead, Thomas L. Lee, Peng Gu +2
Probabilistic forecasting is increasingly critical across high-stakes domains, from finance and epidemiology to climate science. However, current evaluation frameworks lack a conse…
Forgetting is Everywhere
Ben Sanati, Thomas L. Lee, Trevor McInroe +4
A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge as they adapt to new data. Addressing this problem requires a principle…
Hyperparameter Selection in Continual Learning
Thomas L. Lee, Sigrid Passano Hellan, Linus Ericsson +2
In continual learning (CL) -- where a learner trains on a stream of data -- standard hyperparameter optimisation (HPO) cannot be applied, as a learner does not have access to all o…
Chunking: Continual Learning is not just about Distribution Shift
Thomas L. Lee, Amos Storkey
Work on continual learning (CL) has thus far largely focused on the problems arising from shifts in the data distribution. However, CL can be decomposed into two sub-problems: (a)…
Approximate Bayesian Class-Conditional Models under Continuous Representation Shift
Thomas L. Lee, Amos Storkey
For models consisting of a classifier in some representation space, learning online from a non-stationary data stream often necessitates changes in the representation. So, the ques…