Risk-Sensitive Non-Parametric and Kernel Bandits
Devdan Dey, Sujoy Bhore, Avishek Ghosh
Abstract
We study non-parametric bandits in which arms are evaluated using Cumulative Prospect Theory (CPT) rather than expected reward. We consider continuous action spaces with arm-dependent noise and propose Non-Parametric CPT Bandits (NPCB), an optimistic algorithm that decouples mean estimation from CPT-based decision-making. We prove CPT regret of order O(T\,E( F,T-2)\, N( F,T-2,\|·\|∞)), where E is the Eluder dimension of the function class F, T is the time horizon, and N is its covering number in the sup norm. This matches the order-wise regret of classical non-parametric bandits, showing that CPT risk sensitivity incurs no additional order-wise regret cost. We extend NPCB to unknown noise CDFs, retaining the known-CDF mean-learning term and adding a CDF-learning cost governed by a distributional Eluder dimension. We also study Kernel-CPT bandits and obtain information-gain-based regret bounds for a broad range of kernels, matching the corresponding risk-neutral kernel rates up to logarithmic factors.
Create a lesson
Related papers
Quantifying structural stability of transparent models for general insurance pricing
Félix Côté, Marie-Pier Côté
Prevalence Bounds for Edited Watermarked Text: Power Envelopes and Calibration Sensitivity
Kuancheng Ye
Stochastic Kernel Mode Decomposition: Information, Uncertainty, and Conditional Regime Inference
Boumediene Hamzi, Houman Owhadi
When and How SignSGD Outperforms SGD: A Functional Scaling Law Perspective
Zilin Wang, Binghui Li, Jia-Nan Wang et al.
Distribution-First Framework for Learning Risk-Sensitive Individualized Treatment Rules
Zhen Fang, Guanting Chen, Yufeng Liu
Global-Local and Window-Concatenated Functional Random Forests: Early and Late Fusion of Window-Specific Functional Principal Components
Fabrizio Maturo, Annamaria Porreca