3 papers
cs.LG2026
Causal Atlases from Entropic Inference: Bayesian Networks beyond Optimal DAGs
Hazhir Aliahmadi, Irina Babayan, Greg van Anders
Data-driven causal relationship identification is pertinent to advancing understanding of complex systems both within and beyond science. Bayesian networks offer a probabilistic me…
cs.LG2026
Entropic Auto-Encoding via Implicit Free-Energy Minimization
Hazhir Aliahmadi, Irina Babayan, Greg van Anders
Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a failure mode in which latent variables are effectively ignored. This failure ar…
cs.LG2025
Simmering: Sufficient is better than optimal for training neural networks
Irina Babayan, Hazhir Aliahmadi, Greg van Anders
The broad range of neural network training techniques that invoke optimization but rely on ad hoc modification for validity suggests that optimization-based training is misguided.…