Conference paper
Provably Powerful Graph Neural Networks for Directed Multigraphs
Béni Egressy, Luc von Niederhäusern, et al.
AAAI 2024
We study the convergence of a random iterative sequence of a family of operators on infinite-dimensional Hilbert spaces, inspired by the stochastic gradient descent (SGD) algorithm in the case of the noiseless regression. We identify conditions that are strictly broader than previously known for polynomial convergence rate in various norms, and characterize the roles the randomness plays in determining the best multiplicative constants. Additionally, we prove almost sure convergence of the sequence.
Béni Egressy, Luc von Niederhäusern, et al.
AAAI 2024
Lazar Valkov, Akash Srivastava, et al.
ICLR 2024
Yidi Wu, Thomas Bohnstingl, et al.
ICML 2025
Naoki Abe, Kathleen Buckingham, et al.
KDD 2023