Bayesian inference in the space of functions has been an important topic for Bayesian modeling in the past. In this paper, we propose a new solution to this problem called Functional V ariational Inference (FVI). In FVI, we minimize a divergence in function space between the variational distribution and the posterior process.

Each step replaces the two most similar clusters by its union.

Mahmoud Assran et al. "Stochastic Gradient Push for Distributed Deep Learning". Keith Bonawitz et al. "Practical secure aggregation for privacy-preserving machine learning". Pierre Courtiol et al. "Deep learning-based classification of mesothelioma improves prediction "Distributed nonconvex optimization over time-varying networks". "Dual Averaging for Distributed Optimization: Matt Fredrikson, Somesh Jha, and Thomas Ristenpart. "Model inversion attacks that exploit Transactions on The Built Environment 37 (1998). Zhanhong Jiang et al. "Collaborative deep learning in fixed topology networks". Can Karakus et al. "Straggler Mitigation in Distributed Optimization Through Data Encoding". "Federated Optimization:Distributed Optimization Beyond the Datacenter". Jakub Konecný et al. "Federated Optimization: Distributed Machine Learning for On-Device Songze Li et al. "Near-Optimal Straggler Mitigation for Distributed Gradient Methods".

This section complements Section 2 in the main paper by incorporating extra details (Sections A.1

We introduce a semidefinite programming hierarchy to estimate the global and local Lipschitz constant of a multiple layer deep neural network.