Logarithmic regret algorithms for online convex optimization
From MaRDI portal
Publication:1009221
DOI10.1007/s10994-007-5016-8zbMath1471.68327OpenAlexW2129160848MaRDI QIDQ1009221
Amit Agarwal, Satyen Kale, Elad Hazan
Publication date: 31 March 2009
Published in: Machine Learning (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10994-007-5016-8
Convex programming (90C25) Learning and adaptive systems in artificial intelligence (68T05) Portfolio theory (91G10) Online algorithms; streaming algorithms (68W27)
Related Items (52)
No Regret Learning in Oligopolies: Cournot vs. Bertrand ⋮ Sketch-based empirical natural gradient methods for deep learning ⋮ Online active classification via margin-based and feature-based label queries ⋮ Unnamed Item ⋮ Two queues with non-stochastic arrivals ⋮ Portfolio selection algorithm under financial crisis: a case study with Bursa Malaysia ⋮ Predictive online convex optimization ⋮ Online strongly convex optimization with unknown delays ⋮ Improving kernel online learning with a snapshot memory ⋮ Group parking permit problems ⋮ Logarithmic regret in online linear quadratic control using Riccati updates ⋮ Distributed one-pass online AUC maximization ⋮ Real-Time Regression Analysis of Streaming Clustered Data With Possible Abnormal Data Batches ⋮ Distributed online bandit linear regressions with differential privacy ⋮ Adaptive moment estimation for universal portfolio selection strategy ⋮ Online weakly DR-submodular optimization with stochastic long-term constraints ⋮ Online bandit convex optimisation with stochastic constraints via two-point feedback ⋮ Unnamed Item ⋮ No-regret learning for repeated non-cooperative games with lossy bandits ⋮ Online variance minimization ⋮ PAMR: passive aggressive mean reversion strategy for portfolio selection ⋮ Online renewable smooth quantile regression ⋮ Online distributed dual averaging algorithm for multi-agent bandit optimization over time-varying general directed networks ⋮ A Simple Method for Predicting Covariance Matrices of Financial Returns ⋮ Dynamic regret of adaptive gradient methods for strongly convex problems ⋮ Aggregating Algorithm for a Space of Analytic Functions ⋮ Technical Note—Nonstationary Stochastic Optimization Under Lp,q-Variation Measures ⋮ Online First-Order Framework for Robust Convex Optimization ⋮ A generalized online mirror descent with applications to classification and regression ⋮ Kernel-based online regression with canal loss ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Regret bounded by gradual variation for online convex optimization ⋮ Opinion dynamics with limited information ⋮ A modular analysis of adaptive (non-)convex optimization: optimism, composite objectives, variance reduction, and variational bounds ⋮ Scale-invariant unconstrained online learning ⋮ Adaptive sequential machine learning ⋮ Concave switching in single-hop and multihop networks ⋮ Online Bayesian max-margin subspace learning for multi-view classification and regression ⋮ The recursive variational Gaussian approximation (R-VGA) ⋮ Competitive Portfolio Selection Using Stochastic Predictions ⋮ An adaptive online learning algorithm for distributed convex optimization with coupled constraints over unbalanced directed graphs ⋮ Convergence Rate of Incremental Gradient and Incremental Newton Methods ⋮ Warranty optimization in a dynamic environment ⋮ AN ONLINE PORTFOLIO SELECTION ALGORITHM WITH REGRET LOGARITHMIC IN PRICE VARIATION ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Portfolio selection in non-stationary markets ⋮ Suboptimality of constrained least squares and improvements via non-linear predictors ⋮ Small-Loss Bounds for Online Learning with Partial Information ⋮ Online learning over a decentralized network through ADMM
Cites Work
- Unnamed Item
- Unnamed Item
- Applications of second-order cone programming
- A new algorithm for minimizing convex functions over convex sets
- Universal portfolios with and without transaction costs.
- Efficient algorithms for online decision problems
- Universal Portfolios
- 10.1162/153244303321897672
- Prediction, Learning, and Games
- Communicating Sequential Processes. The First 25 Years
- Stochastic nonstationary optimization for finding universal portfolios
- Relative loss bounds for multidimensional regression problems
This page was built for publication: Logarithmic regret algorithms for online convex optimization