Online Gradient Descent
Abstract
In this chapterwe introduce an idea that is ubiquitous in zeroth-order optimisation, which is to use a gradient-based algorithm but replace the true gradients with estimated gradients of a smoothed loss. Except for Section 5.4, we assume throughout this chapter that the constraint set contains a euclidean ball of unit radius, the losses are bounded, Lipschitz and there is no noise:
Fields of Study & Subjects
Stochastic Gradient Optimization Techniques
Advanced Bandit Algorithms Research
Advanced Optimization Algorithms Research
Publication details
- Journal / source
- Cambridge University Press eBooks
- Pages
- 50–60
- Publication date
- 7 March 2026
- Language
- EN
- Document type
- Book chapter