Stochastic online convex optimization. Application to probabilistic time series forecasting
Open Access
- 1 January 2024
- journal article
- research article
- Published by Institute of Mathematical Statistics in Electronic Journal of Statistics
- Vol. 18 (1) , 429-464
Abstract
In this paper, we propose a general framework for stochastic online convex optimization that allows for achieving fast-rate stochastic regret bounds. Specifically, we demonstrate that certain algorithms, including online Newton steps and a scale-free variant of Bernstein online aggregation, achieve the best-known rates in unbounded stochastic settings. To illustrate the usefulness of our approach, we apply it to calibrating parametric probabilistic forecasters of non-stationary sub-Gaussian time series. Importantly, our fast-rate stochastic regret bounds are valid at any time, providing a flexible and robust performance metric for sequential algorithms. Our proofs rely on combining self-bounded and Poissonian inequalities for martingales and sub-Gaussian random variables, respectively, under a stochastic exp-concavity assumption.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Online learning with the Continuous Ranked Probability Score for ensemble forecastingQuarterly Journal of the Royal Meteorological Society, 2016
- The Bernstein–Orlicz norm and deviation inequalitiesProbability Theory and Related Fields, 2012
- Estimating conditional quantiles with the help of the pinball lossBernoulli, 2011
- Volatility forecast comparison using imperfect volatility proxiesJournal of Econometrics, 2011
- Inconsistency of the MLE and inference based on weighted LS for LARCH modelsJournal of Econometrics, 2010
- Exponential inequalities for self-normalized martingales with applicationsThe Annals of Applied Probability, 2008
- Learning by mirror averagingThe Annals of Statistics, 2008
- Strictly Proper Scoring Rules, Prediction, and EstimationJournal of the American Statistical Association, 2007
- Improved second-order bounds for prediction with expert adviceMachine Learning, 2006
- On Tail Probabilities for MartingalesThe Annals of Probability, 1975