Optimizing the marginal likelihood encoding the idea of Occam's razor leads to more sparsifiable neural networks. The title is 🔥
Alex Immer
📢 Excited to present our work at #NeurIPS2024!
📄 "Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood"
Read it here: arxiv.org/abs/2402.15978
Details in 🧵
