2000 character limit reached
Sharp Finite-Time Iterated-Logarithm Martingale Concentration
Published 12 May 2014 in math.PR, cs.LG, and stat.ML | (1405.2639v4)
Abstract: We give concentration bounds for martingales that are uniform over finite times and extend classical Hoeffding and Bernstein inequalities. We also demonstrate our concentration bounds to be optimal with a matching anti-concentration inequality, proved using the same method. Together these constitute a finite-time version of the law of the iterated logarithm, and shed light on the relationship between it and the central limit theorem.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.