Sequential complexities and uniform martingale laws of large numbers
By Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari. 2015
122 citations recorded by the source corpus.
Subfields: Finance, Management Science and Operations Research, Statistics and Probability
View Paper: https://www.semanticscholar.org/paper/2148f4f53e4d6b1a97982d7446ab9fcb6be08f72
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Finance
In Management Science and Operations Research
In Statistics and Probability
Citations in the corpus
- Learning Theory and Algorithms for Forecasting Non-stationary Time Series (2015, methodology): “In a similar manner, one can define other measures of complexity such as sequential Rademacher complexity and the Littlestone dimension [Rakhlin et al., 2015] as well as their data-dependent counterparts [Rakhlin et al., 2011].”
- Time series prediction and online learning (2016, methodology): “The guarantees that we present are in terms of the expected sequential covering numbers Ez∼ZT [N1(α,F , z)] of the set F = {(z, t) 7→ L(ht, z) : h ∈ HA} which are natural generalizations to the sequential setting of the standard expected covering numbers (Rakhlin et al., 2015b).”