Causal Inference via Predictive Coding

no code implementations • 27 Jun 2023 • Tommaso Salvatori, Luca Pinchetti, Amine M'Charrak, Beren Millidge, Thomas Lukasiewicz

Bayesian inference models observations: what can be inferred about y if we observe a related variable x?

Bayesian Inference Causal Discovery +2

Tighter Variational Bounds are Not Necessarily Better. A Research Report on Implementation, Ablation Study, and Extensions

1 code implementation • 23 Sep 2022 • Amine M'Charrak, Vít Růžička, Sangyun Shin, Madhu Vankadari

We provide theoretical and empirical evidence that increasing the number of importance samples $K$ in the importance weighted autoencoder (IWAE) (Burda et al., 2016) degrades the signal-to-noise ratio (SNR) of the gradient estimator in the inference network and thereby affecting the full learning process.