Joudaki, Amir

9 publications

ICLR 2026 Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity Amir Joudaki, Giulia Lanzillotta, Mohammad Samragh, Seyed Iman Mirzadeh, Keivan Alizadeh, Thomas Hofmann, Mehrdad Farajtabar, Fartash Faghri

AISTATS 2025 Emergence of Globally Attracting Fixed Points in Deep Neural Networks with Nonlinear Activations Amir Joudaki, Thomas Hofmann

ICMLW 2024 Identifying Biological Priors and Structure in Single-Cell Foundation Models Flavia Pedrocchi, Stefan Stark, Gunnar Ratsch, Amir Joudaki

ICLR 2024 Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion Alexandru Meterez, Amir Joudaki, Francesco Orabona, Alexander Immer, Gunnar Ratsch, Hadi Daneshmand

NeurIPSW 2023 Learning Genomic Sequence Representations Using Graph Neural Networks over De Bruijn Graphs Kacper Kapusniak, Manuel Burger, Gunnar Ratsch, Amir Joudaki

ICML 2023 On Bridging the Gap Between Mean Field and Finite Width Deep Random Multilayer Perceptron with Batch Normalization Amir Joudaki, Hadi Daneshmand, Francis Bach

NeurIPS 2023 On the Impact of Activation and Normalization in Obtaining Isometric Embeddings at Initialization Amir Joudaki, Hadi Daneshmand, Francis R. Bach

NeurIPS 2021 Batch Normalization Orthogonalizes Representations in Deep Random Networks Hadi Daneshmand, Amir Joudaki, Francis R. Bach

NeurIPSW 2021 PCA Subspaces Are Not Always Optimal for Bayesian Learning Alexandre Bense, Amir Joudaki, Tim G. J. Rudner, Vincent Fortuin