F
Fredrik Lindsten
Researcher at Linköping University
Publications - 132
Citations - 3077
Fredrik Lindsten is an academic researcher from Linköping University. The author has contributed to research in topics: Particle filter & Markov chain Monte Carlo. The author has an hindex of 30, co-authored 120 publications receiving 2601 citations. Previous affiliations of Fredrik Lindsten include Uppsala University & University of Cambridge.
Papers
More filters
Paper index
Yaron Laufer,Sharon Gannot,Jakob Lindqvist,Amanda Olmin,Fredrik Lindsten,Marco Prato,Emilie Chouzenoux +6 more
Book ChapterDOI
Active Learning with Weak Supervision for Gaussian Processes
TL;DR: This paper proposed an active learning algorithm that, in addition to selecting which observation to annotate, selects the precision of the annotation that is acquired, assuming that annotations with low precision are cheaper to obtain, this allows the model to explore a larger part of the input space, with the same annotation budget.
UvA-DARE (Digital Academic Repository) A Variational Perspective on Generative Flow Networks
TL;DR: In this paper , a variational objective for training GNNs is introduced, which is a convex combination of the reverse-and forward KL divergences, and compare it to the trajectory balance objective when sampling from the forward and backward model, respectively.
Marginalized particle Gibbs for multiple state-space models coupled through shared parameters
Anna Wigren,Fredrik Lindsten +1 more
TL;DR: Two different PG samplers that marginalize static model parameters on-the-fly are presented: one that updates one model at a time conditioned on the datasets for the other models, and one that concurrently updates all models by stacking them into a high-dimensional SSM.
Journal ArticleDOI
Active Learning with Weak Labels for Gaussian Processes
TL;DR: An active learning algorithm is proposed that, in addition to selecting which observation to annotate, selects the precision of the annotation that is acquired, which allows the model to explore a larger part of the input space, with the same annotation costs.