Introduction to Online Optimization

By Sébastien Bubeck. 2011

166 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Decentralized Online Learning: Take Benefits from Others’ Data without Sharing Your Own to Track Global Trend (2019, methodology): “The static regret of a sequential online convex optimization method can achieve O √ T and O (log T ) bounds for convex and strongly convex loss functions, respectively [Hazan, 2016, Shalev-Shwartz, 2012, Bubeck, 2011].”
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (2012, neutral): “The connection between existing online learning algorithms (such as Exponential weights or Online Gradient Descent) and Mirror Descent was first made explicit in Cesa-Bianchi and Lugosi [2006] —see also Rakhlin [2009] and Hazan [2011].”
Efficient Tracking of Large Classes of Experts (2011, methodology): “made, e.g., the gradient of the loss function is bounded, the online Newton step algorithm of [12] can be applied to achieve logarithmic (standard) regret against the base-expert class E. We refer to [33] for a survey. F. The weight function wKT In this section we analyze the performance of Algorith”
Towards Minimax Policies for Online Linear Optimization with Bandit Feedback (2012, methodology): “In the full information setting (when one observes zt), we have a very good understanding of how to use Mirror Descent to obtain optimal regret bounds that adapt to the geometry of the problem —see (Rakhlin, 2009; Hazan, 2011; Bubeck, 2011).”
Understand Dynamic Regret with Switching Cost for Online Decision Making (2019, methodology): “1 Online algorithms and online convex optimization Comparing with the seing of OCO [9, 23, 38], OA has the following major dierence.”
Online distributed optimization via dual averaging (2013, background): “Further discussion on online algorithms and their regret can be found in [16], [17], [18].”
Convex Optimization: Algorithms and Complexity (2014, methodology): “Curiously we note that one of those walks is closely connected to projected gradient descent, see Bubeck et al. [2015a].”
Dynamic Language Models for Streaming Text (2014, background): “See Cesa-Bianchi and Lugosi (2006), Rakhlin (2009), Bubeck (2011), and Shalev-Shwartz (2012) for in-depth discussion and review.”