collaborators

5 papers

cs.LG2026

Closed-Form Last Layer Optimization

Alexandre Galashov, Nathaël Da Costa, Liyuan Xu +2

Neural networks are typically optimized with variants of stochastic gradient descent. Under a squared loss, however, the optimal solution to the linear last layer weights is known…

cs.LG2026

Rethinking Approximate Gaussian Inference in Classification

Bálint Mucsányi, Nathaël Da Costa, Philipp Hennig

In classification tasks, softmax functions are ubiquitously used as output activations to produce predictive probabilities. Such outputs only capture aleatoric uncertainty. To capt…

cs.LG2025

laplax -- Laplace Approximations with JAX

Tobias Weber, Bálint Mucsányi, Lenard Rommel +4

The Laplace approximation provides a scalable and efficient means of quantifying weight-space uncertainty in deep neural networks, enabling the application of Bayesian tools such a…

math.DG2025

Geometric Gaussian Approximations of Probability Distributions

Nathaël Da Costa, Bálint Mucsányi, Philipp Hennig

Approximating complex probability distributions, such as Bayesian posterior distributions, is of central interest in many applications. We study the expressivity of geometric Gauss…

cs.LG2025

Debiasing Mini-Batch Quadratics for Applications in Deep Learning

Lukas Tatzel, Bálint Mucsányi, Osane Hackel +1

Quadratic approximations form a fundamental building block of machine learning methods. E.g., second-order optimizers try to find the Newton step into the minimum of a local quadra…