Statistical learning with sublinear regret of propagator models

DOI10.1214/25-AAP2155MaRDI QIDQ7320979zbMATH OpenFDO

Authors Eyal Neuman, Yufei Zhang

Publication date 28 August 2026

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

Full work available at URL https://projecteuclid.org/journals/annals-of-applied-probability/volume-36/issue-4/Statistical-learning-with-sublinear-regret-of-propagator-models/10.1214/25-AAP2155.full

Mathematics Subject Classification ID

Applications of stochastic analysis (to PDEs, etc.) (60H30) Nonparametric regression and quantile regression (62G08) Sequential statistical design (62L05) Computational learning theory (68Q32) Financial applications of other theories (91G80) Stochastic learning and adaptive control (93E35)

Cites work

• A distribution-free theory of nonparametric regression
• Algorithmic and high-frequency trading
• Approximate source conditions in Tikhonov regularization -- new analytical results and some numerical studies
• Backward stochastic differential equations with jumps and their actuarial and financial applications. BSDEs with jumps
• Bandit algorithms
• Convergence analysis of Tikhonov regularization for non-linear statistical inverse problems
• Do fundamentals shape the price response? A critical assessment of linear impact models
• Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models
• Fluctuations and response in financial markets: the subtle nature of `random' price changes
• Functional linear regression with functional response
• scientific article; zbMATH DE number 3868512 (Why is no real title available?)
• scientific article; zbMATH DE number 5190601 (Why is no real title available?)
• scientific article; zbMATH DE number 44608 (Why is no real title available?)
• scientific article; zbMATH DE number 1325009 (Why is no real title available?)
• scientific article; zbMATH DE number 194918 (Why is no real title available?)
• scientific article; zbMATH DE number 1376935 (Why is no real title available?)
• scientific article; zbMATH DE number 936298 (Why is no real title available?)
• Incorporating order-flow into optimal execution
• Incorporating signals into optimal trading
• Linear models for the impact of order flow on prices. I. History dependent impact models
• Liquidity Models in Continuous and Discrete Time
• Logarithmic regret bounds for continuous-time average-reward Markov decision processes
• No-dynamic-arbitrage and market impact
• On the sample complexity of the linear quadratic regulator
• Optimal liquidation with signals: the general propagator case
• Optimal portfolio liquidation in target zone models and catalytic superprocesses
• Optimal rates for regularization of statistical inverse learning problems
• Optimal Scheduling of Entropy Regularizer for Continuous-Time Linear-Quadratic Reinforcement Learning
• Optimal Signal-Adaptive Trading with Temporary and Transient Price Impact
• Optimal trade execution for Gaussian signals with power-law resilience
• Reinforcement Learning for Linear-Convex Models with Jumps via Stability Analysis of Feedback Controls
• Square-root regret bounds for continuous-time episodic Markov decision processes
• The financial mathematics of market liquidity. From optimal execution to market making
• Trading with the crowd
• Transient linear price impact and Fredholm integral equations

This page was built for publication: Statistical learning with sublinear regret of propagator models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7320979)