Klas Wijk — accepted AI-conference papers

2025

SFESS: Score Function Estimators for $k$-Subset Sampling

Klas Wijk, Ricardo Vinuesa, Hossein Azizpour

ICLR 2025poster

Are score function estimators a viable approach to learning with $k$-subset sampling? Sampling $k$-subsets is a fundamental operation that is not amenable to differentiable parametrization, impeding gradient-based optimization. Previous work has favored approximate pathwise gradients or relaxed samp…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Indirectly Parameterized Concrete Autoencoders

Alfred Nilsson, Klas Wijk, Sai bharath chandra Gutha, Erik Englesson, Alexandra Hotti, Carlo Saccardi +4

ICML 2024poster

Feature selection is a crucial task in settings where data is high-dimensional or acquiring the full set of features is costly. Recent developments in neural network-based embedded feature selection show promising results across a wide range of applications. Concrete Autoencoders (CAEs), considered…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗