A Variant of Azuma's Inequality for Martingales with Subgaussian Tails
By Ohad Shamir. 2011
40 citations recorded by the source corpus.
We provide a variant of Azuma's concentration inequality for martingales, in which the standard boundedness requirement is replaced by the milder requirement of a subgaussian tail.
Subfields: Applied Mathematics, Mathematical Physics, Statistical Learning Theory, Pure Mathematics
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Applied Mathematics
In Mathematical Physics
In Statistical Learning Theory
In Pure Mathematics
Citations in the corpus
- A Convergence Theory for Deep Learning via Over-Parameterization (2018, background): “Using martingale concentration on subgaussian variables (see for instance [45]), we have for ε ∈ (0 , 1], Since with probability ≥ 1 − Le − Ω( m ) it satisfies (cid:98) ∆ (cid:96) = ∆ (cid:96) for all (cid:96) ∈ [ L ], combining this with (4.1), we have In other words,”