Fast Probabilistic Optimization from Noisy Gradients

By Philipp Hennig. 2013

35 citations recorded by the source corpus.

Subfields: Optimization & Training

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Optimization & Training

1. Surya Ganguli
2. Ben Poole
3. Jascha Narain Sohl-Dickstein
4. Katya Scheinberg
5. Courtney Paquette
6. Martin Kiefel
7. Philipp Hennig
8. Greg Yang

Citations in the corpus

• Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods (2013, methodology): “In (Hennig, 2013) a nonparametric quasi-Newton algorithm is proposed based on noisy gradient observations and a Gaussian process prior.”
• A Stochastic Line Search Method with Convergence Rate Analysis (2018, background): “Various authors have attempted to address this last issue, see [8, 10, 12, 13].”
• Probabilistic numerics and uncertainty in computations (2015, unknown): “Among other things, this allows explicit modelling of noise on evaluated gradients, a pressing issue in large-scale machine learning [40].”
• Quasi-Newton Methods: A New Direction (2012, background): “An upcoming conference paper (Hennig, 2013) will study how this can be used to construct optimizers robust to noise.”