Arnaud Capitaine

AI

Exploring New Hyperparameter Dimensions with Laplace Approximated Bayesian Optimization

Is it better than grid search? Arnaud Capitaine · Follow Published in Towards Data Science · 9 min read · 11 hours ago — Image by author from canva When I notice my model is overfitting, I often think, “It is time to regularize”. But how do I decide which regularization method to use (L1, L2) and what parameters to choose? Typically, I perform hyperparameter optimization by means of a grid search to select the

Read More »
AI

Adapted Prediction Intervals by Means of Conformal Predictions and a Custom Non-Conformity Score

How confident should I be in a machine learning model’s prediction for a new data point? Could I get a range of likely values? Arnaud Capitaine · Follow Published in Towards Data Science · 9 min read · Jan 24, 2024 — Image by author When working on a supervised task, machine learning models can be used to predict the outcome for new samples. However, it is likely that the prediction from a new data

Read More »