3 papers
stat.CO2026
A thermodynamic approach to Approximate Bayesian Computation with multiple summary statistics
Carlo Albert, Simone Ulzega, Simon Dirmeier +3
Bayesian inference with stochastic models is often difficult because their likelihood functions involve high-dimensional integrals. Approximate Bayesian Computation (ABC) avoids ev…
cs.LG2026
Simulation-based Inference with the Python Package sbijax
Simon Dirmeier, Antonietta Mira, Carlo Albert
Neural simulation-based inference (SBI) describes an emerging family of methods for Bayesian inference with intractable likelihood functions that use neural networks as surrogate m…
cs.LG2026
When Bias Meets Trainability: Connecting Theories of Initialization
Alberto Bassi, Marco Baity-Jesi, Aurelien Lucchi +2
The statistical properties of deep neural networks (DNNs) at initialization play an important role to comprehend their trainability and the intrinsic architectural biases they poss…