3 papers
eess.SY2026
Importance Sampling for Statistical Certification of Viable Initial Sets
Elizabeth Dietrich, Hanna Krasowski, Vegard Flovik +1
We study the problem of statistically certifying viable initial sets (VISs)---sets of initial conditions whose trajectories satisfy a given control specification. While VISs can be…
cs.LG2026
SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks
Vegard Flovik
Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover,…
cs.LG2025
Gaussian Process Surrogate Models for Efficient Estimation of Structural Response Distributions and Order Statistics
Vegard Flovik, Sebastian Winter, Christian Agrell
Engineering disciplines often rely on extensive simulations to ensure that structures are designed to withstand harsh conditions while avoiding over-engineering for unlikely scenar…