Approximating Hessian matrices using Bayesian inference: a new approach for quasi-Newton methods in stochastic optimization
(2024)
Journal Article
Carlon, A. G., Espath, L., & Tempone, R. (2024). Approximating Hessian matrices using Bayesian inference: a new approach for quasi-Newton methods in stochastic optimization. Optimization Methods and Software, https://doi.org/10.1080/10556788.2024.2339226
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.