34 citations · 87 across the 9 of their papers we have counts for
3 papers · 1 filter
A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings
Théophile Cantelobre, Benjamin Guedj, María Pérez-Ortiz +1
Many practical machine learning tasks can be framed as Structured prediction problems, where several output variables are predicted and considered interdependent. Recent theoretica…
Tighter risk certificates for neural networks
María Pérez-Ortiz, Omar Rivasplata, John Shawe-Taylor +1
This paper presents an empirical study regarding training probabilistic neural networks using training objectives derived from PAC-Bayes bounds. In the context of probabilistic neu…
Predicting Engagement in Video Lectures
Sahan Bulathwela, María Pérez-Ortiz, Aldo Lipani +2
The explosion of Open Educational Resources (OERs) in the recent years creates the demand for scalable, automatic approaches to process and evaluate OERs, with the end goal of iden…