Self-normalized processes: exponential inequalities, moment bounds and iterated logarithm laws.

DOI10.1214/009117904000000397zbMath1075.60014arXivmath/0410102OpenAlexW3101257511MaRDI QIDQ1879810

Michael J. Klass, Victor H. de la Peña, Tze Leung Lai

Publication date: 15 September 2004

Published in: The Annals of Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/math/0410102

zbMATH Keywords

law of the iterated logarithmmoment inequalities

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Martingales with discrete parameter (60G42) Martingales with continuous parameter (60G44)

Related Items

Exponential inequalities for unbounded functions of geometrically ergodic Markov chains: applications to quantitative error bounds for regenerative Metropolis algorithms, Woodroofe's one-armed bandit problem revisited, Exact inequalities for sums of asymmetric random variables, with applications, Solving optimal stopping problems via empirical dual optimization, Tightened exponential bounds for discrete-time conditionally symmetric martingales with bounded jumps, Time-uniform Chernoff bounds via nonnegative supermartingales, Encounters with Martingales in Statistics and Stochastic Optimization, Precise asymptotics in the deviation probability series of self-normalized sums, Drift estimation for a multi-dimensional diffusion process using deep neural networks, Exponential inequalities and the law of the iterated logarithm in the unbounded forecasting game, An almost sure central limit theorem for self-normalized weighted sums, Sequential testing for elicitable functionals via supermartingales, On the convex Poincaré inequality and weak transportation inequalities, An exponential inequality for autoregressive processes in adaptive tracking, Unnamed Item, A law of large numbers for interacting diffusions via a mild formulation, Spiking the random matrix hard edge, Exponential inequalities for self-normalized martingales with applications, Cramér-type large deviations for samples from a finite population, Time-uniform, nonparametric, nonasymptotic confidence sequences, Precise asymptotics in complete moment convergence for self-normalized sums, Theory and applications of multivariate self-normalized processes, Matrices -- compensating the loss of anschauung, On the Bias, Risk, and Consistency of Sample Means in Multi-armed Bandits, Long time dynamics for interacting oscillators on graphs

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Some extensions of the LIL via self-normalizations
• Upper bounds for the \(L_ p\)-norms of martingales
• Another note on the Borel-Cantelli lemma and the strong law, with the Poisson approximation as a by-product
• Boundary crossing probabilities for sample sums and confidence sequences
• Self-normalized laws of the iterated logarithm
• Estimation of densities and applications
• On the LIL for self-normalized sums of IID random variables
• Probabilistic behavior of harmonic functions
• Self-normalized large deviations
• When is the Student \(t\)-statistic asymptotically standard normal?
• Self-normalized Cramér-type large deviations for independent random variables.
• A comparison theorem on moment inequalities between negatively associated and independent random variables
• A general class of exponential inequalities for martingales and ratios
• The Berry-Esseen bound for Student's statistic
• Maximal inequalities and the law of the iterated logarithm
• Improved ratio inequalities for martingales
• Inequalities for a Pair of Processes Stopped at a Random Time
• A Delicate Law of the Iterated Logarithm for Non-Decreasing Stable Processes
• Boundary Crossing Probabilities for the Wiener Process and Sample Sums