We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Along with Markov chain Monte Carlo (MCMC) methods, variational inference (VI) has emerged as a central computational approach to large-scale Bayesian inference. Rather than sampling from the true posterior $π$, VI aims at producing a simple but effective approximation $\hat π$ to $π$ for which summary statistics are easy to compute. However, unlike the well-studied MCMC methodology, algorithmic guarantees for VI are still relatively less well-understood. In this work, we propose principled methods for VI, in which $\hat π$ is taken to be a Gaussian or a mixture of Gaussians, which rest upon the theory of gradient flows on the Bures--Wasserstein space of Gaussian measures. Akin to MCMC, it comes with strong theoretical guarantees when $π$ is log-concave.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.15902")
get_code_for_paper("2205.15902")
have("2205.15902")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.15902.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.15902)
Connect an agent — have() is free.