3 papers
cs.LG2026
A Stein Identity for q-Gaussians with Bounded Support
Sophia Sklaviadis, Thomas Moellenhoff, Andre F. T. Martins +2
Stein's identity is a fundamental tool in machine learning with applications in generative models, stochastic optimization, and other problems involving gradients of expectations u…
cs.LG2026
Fenchel-Young Variational Learning
Sophia Sklaviadis, Thomas Moellenhoff, Andre Martins +1
From a variational perspective, many statistical learning criteria involve seeking a distribution that balances empirical risk and regularization. In this paper, we broaden this pe…
cs.LG2025
Sparse Activations as Conformal Predictors
Margarida M. Campos, João Calém, Sophia Sklaviadis +2
Conformal prediction is a distribution-free framework for uncertainty quantification that replaces point predictions with sets, offering marginal coverage guarantees (i.e., ensurin…