Optimal anytime regret with two experts
From MaRDI portal
Publication:6062702
DOI10.4171/msl/38arXiv2002.08994OpenAlexW3008672633MaRDI QIDQ6062702
Christopher Liaw, Sikander Randhawa, Edwin A. Perkins, Nicholas J. A. Harvey
Publication date: 6 November 2023
Published in: Mathematical Statistics and Learning (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2002.08994
Computational learning theory (68Q32) Convex sets in (n) dimensions (including convex hypersurfaces) (52A20) General considerations in statistical decision theory (62C05)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Primal-dual subgradient methods for convex problems
- Brownian motion hitting probabilities for general two-sided square-root boundaries
- A conditioned limit theorem for random walk and Brownian local time on square root boundaries
- Ito's formula for a random walk
- On the \(L^p\) norms of stochastic integrals and other martingales
- The weighted majority algorithm
- Optimal learning and experimentation in bandit problems.
- Analysis of two gradient-based algorithms for on-line regression
- On the asymptotic optimality of the comb strategy for prediction with expert advice
- Prediction with expert advice: a PDE perspective
- Probability theory. A comprehensive course.
- Online trading algorithms and robust option pricing
- On a Property of Real Plane Curves of Even Degree
- Online Learning and Online Convex Optimization
- Probability with Martingales
- How to use expert advice
- Probability
- Towards Optimal Algorithms for Prediction with Expert Advice
- On the Hausdorff dimension of the Brownian slow points
- Tight Lower Bounds for Multiplicative Weights Algorithmic Families
- Finite-time 4-expert prediction problem
- A random walk analogue of Lévy’s Theorem
- Minimax option pricing meets black-scholes in the limit
- Prediction, Learning, and Games
- A First Passage Problem for the Wiener Process