4 papers
Too much of a good thing -- when knowledge distillation promotes overfitting, and how to avoid it
Irene Trigueros-Lorca, Leonardo Concepción, Christian Wagner +2
The growing size of Convolutional Neural Networks has led to increasingly large and costly models. Knowledge Distillation (KD) addresses this by transferring knowledge from a large…
LUCoS: Latent Unsupervised Context Selection for Tabular Foundation Models
Oroel Ipas, Guillermo Gomez-Trenado, RocÃo Romero-Zaliz +1
Selecting which instances to label is a key challenge in low-label tabular learning. For recent Tabular Foundation Models such as TabPFN, context selection directly determines pred…
VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection
Alberto D. Cencillo, Leonardo Concepción, Isaac Triguero +1
Anomaly detection in multivariate time series is a critical task across a wide range of real-world applications, where abnormal behaviour is rare, labels are unavailable, and the c…
Decision-Focused Learning Enhanced by Automated Feature Engineering for Energy Storage Optimisation
Nasser Alkhulaifi, Ismail Gokay Dogan, Timothy R. Cargan +4
Decision-making under uncertainty in energy management is complicated by unknown parameters hindering optimal strategies, particularly in Battery Energy Storage System (BESS) opera…