2 papers
cs.LG2022
Fine-tune your Classifier: Finding Correlations With Temperature
Benjamin Chamand, Olivier Risser-Maroix, Camille Kurtz +2
Temperature is a widely used hyperparameter in various tasks involving neural networks, such as classification or metric learning, whose choice can have a direct impact on the mode…
cs.LG2022
What can we Learn by Predicting Accuracy?
Olivier Risser-Maroix, Benjamin Chamand
This paper seeks to answer the following question: \textit{"What can we learn by predicting accuracy?"}. Indeed, classification is one of the most popular tasks in machine learning…