1 citations · 2 across the 6 of their papers we have counts for
6 papers
Uncertainty Estimation by Human Perception versus Neural Models
Pedro Mendes, Paolo Romano, David Garlan
Modern neural networks (NNs) often achieve high predictive accuracy but are poorly calibrated, producing overconfident predictions even when wrong. This miscalibration poses seriou…
CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignment
Pedro Mendes, Paolo Romano, David Garlan
Reliable uncertainty estimation is critical for deploying neural networks (NNs) in real-world applications. While existing calibration techniques often rely on post-hoc adjustments…
Error-Driven Uncertainty Aware Training
Pedro Mendes, Paolo Romano, David Garlan
Neural networks are often overconfident about their predictions, which undermines their reliability and trustworthiness. In this work, we present a novel technique, named Error-Dri…
Hyper-parameter Tuning for Adversarially Robust Models
Pedro Mendes, Paolo Romano, David Garlan
This work focuses on the problem of hyper-parameter tuning (HPT) for robust (i.e., adversarially trained) models, shedding light on the new challenges and opportunities arising dur…
HyperJump: Accelerating HyperBand via Risk Modelling
Pedro Mendes, Maria Casimiro, Paolo Romano +1
In the literature on hyper-parameter tuning, a number of recent solutions rely on low-fidelity observations (e.g., training with sub-sampled datasets) in order to efficiently ident…
TrimTuner: Efficient Optimization of Machine Learning Jobs in the Cloud via Sub-Sampling
Pedro Mendes, Maria Casimiro, Paolo Romano +1
This work introduces TrimTuner, the first system for optimizing machine learning jobs in the cloud to exploit sub-sampling techniques to reduce the cost of the optimization process…