Data Dependent Concentration Bounds for Sequential Prediction Algorithms

2005

50 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Science and Operations Research

Citations in the corpus

• Adaptive Gradient-Based Meta-Learning Methods (2019, methodology): “This is witnessed by the guarantee for self-bounded losses , a class which Zhang [53] shows includes linear regression; we use a result by the same author to obtain high-probability bounds, whereas previous GBML bounds are in-expectation [35, 20].”
• Introduction to Online Convex Optimization (2016, background): “Tighter and more general bounds were explored in (27; 28; 109).”
• Online Learning and Online Convex Optimization (2012, methodology): “Concentration bounds on the risk of the ensemble that rely on the online loss were derived by Zhang [45] and Cesa-Bianchi et al.”
• Tail inequalities for sums of random matrices that depend on the intrinsic dimension (2012, background): “The following lemma due to Tropp (2011b) is a matrix generalization of a scalar result due to Freedman (1975) (see also Zhang, 2005), where the key is the invocation of Theorem 1.”
• On the Generalization Ability of Online Strongly Convex Programming Algorithms (2008, background): “This paper continues the line of research initiated by several researchers [Littlestone, 1989, Cesa- Bianchi et al., 2004, Zhang, 2005, Cesa-Bianchi and Gentile, 2008] which looks at how to convert online algorithms into batch algorithms with provable guarantees.”
• IEEE TRANSACTIONS ON INFORMATION THEORY , VOL . ? , NO . ? , ? 200 ? 1 Improved Risk Tail Bounds for On-Line Algorithms (2007, unknown): “In independent work [13], Zhang derived a new martingale inequality which he used to prove a bound on the average risk of the ensemble of the form”
• Online Learning: A Comprehensive Survey (2018, methodology): “The work of Zhang [121] is the closest the one in the pre-”