← Search

Jarosław Błasiok

2 accepted papers

2023

When Does Optimizing a Proper Loss Yield Calibration?

NeurIPS 2023spotlight

Optimizing proper loss functions is popularly believed to yield predictors with good calibration properties; the intuition being that for such losses, the global optimum is to predict the ground-truth probabilities, which is indeed calibrated. However, typical machine learning models are trained to…

Cited by 31SourcePDFScholar
2022

What You See is What You Get: Principled Deep Learning via Distributional Generalization

NeurIPS 2022accept

Having similar behavior at training time and test time—what we call a “What You See Is What You Get” (WYSIWYG) property—is desirable in machine learning. Models trained with standard stochastic gradient descent (SGD), however, do not necessarily have this property, as their complex behaviors such as…