Using coins to make Bayesian inference learning-rate free
Blog post on Coin Sampling, a learning-rate-free approach to gradient-based Bayesian inference.
Learning-Rate-Free
Learning-Rate-Free Stochastic Optimization over Riemannian Manifolds
International Conference on Machine Learning (ICML)
Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Betting
International Conference on Artificial Intelligence and Statistics (AISTATS)
Learning Rate Free Sampling in Constrained Domains
Neural Information Processing Systems (NeurIPS)
Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates
International Conference on Machine Learning (ICML)