Approximating Hessian matrices using Bayesian inference: a new approach for quasi-Newton methods in stochastic optimization
(2024)
Journal Article
Using quasi-Newton methods in stochastic optimization is not a trivial task given the difficulty of extracting curvature information from the noisy gradients. Moreover, pre-conditioning noisy gradient observations tend to amplify the noise. We propos... Read More about Approximating Hessian matrices using Bayesian inference: a new approach for quasi-Newton methods in stochastic optimization.