Accepted Papers at ICLR and AISTATS 2025

Four papers from the Helsinki Probabilistic Machine Learning Lab have been accepted at major conferences this January.

One paper will be presented at the International Conference on Learning Representations (ICLR 2025) and three papers have been accepted at the International Conference on Artificial Intelligence and Statistics (AISTATS 2025):
 

  1. Stochastic Variance-Reduced Gaussian Variational Inference on the Bures-Wasserstein Manifold by Luu H. P. H., Yu H., Williams B., Hartmann M., and Klami A.,
    International Conference on Learning Representations (ICLR 2025). [Link]
     
  2. Amortized Probabilistic Conditioning for Optimization, Simulation, and Inference by Chang P. E., Loka N., Huang D., Remes U., Kaski S., and Acerbi L.,
    International Conference on Artificial Intelligence and Statistics (AISTATS 2025). [Link]
     
  3. Noise-Aware Differentially Private Variational Inference by Alrawajfeh T., Jälkö J., Honkela A.,
    International Conference on Artificial Intelligence and Statistics (AISTATS 2025). [Link]
     
  4. A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets by Räisä O., Honkela A.,
    International Conference on Artificial Intelligence and Statistics (AISTATS 2025). [Link]


See our Publications page for more information.

 

Additionally, congratulations to several lab members who had other papers accepted with external collaborators or from previous work: Mikko A. Heikkilä (ICLR), Juha Harviainen (AISTATS), and Daolang Huang (ICLR, AISTATS).