Robustness of Dynamical Quantities of Interest via Goal-Oriented Information Theory

06/21/2019
by   Jeremiah Birrell, et al.
0

Variational-principle-based methods that relate expectations of a quantity of interest to information-theoretic divergences have proven to be effective tools for obtaining robustness bounds under both parametric and non-parametric model-form uncertainty. Here, we extend these ideas to utilize information divergences that are specifically targeted at the quantity-of-interest being investigated; leveraging this specificity results in tighter robustness bounds and expands the class of problems that can be treated. We find the method especially useful for problems involving unbounded time-horizons, a case where established information-theoretic methods only produce trivial bounds. General problem types that can be treated within this framework include the expected value and distribution of a stopping time, time averages, and exponentially discounted observables. We illustrate these results with several examples, including option pricing, stochastic control, semi-Markov processes, and expectations and distributions of hitting times.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/21/2019

Information-Theoretic Confidence Bounds for Reinforcement Learning

We integrate information-theoretic concepts into the design and analysis...
research
09/30/2022

On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits

We lay the foundations of a non-parametric theory of best-arm identifica...
research
10/04/2021

Information-theoretic generalization bounds for black-box learning algorithms

We derive information-theoretic generalization bounds for supervised lea...
research
11/18/2021

Information-theoretic formulation of dynamical systems: causality, modeling, and control

The problems of causality, modeling, and control for chaotic, high-dimen...
research
06/22/2020

Robust uncertainty sensitivity analysis

We consider sensitivity of a generic stochastic optimization problem to ...
research
02/04/2022

Improved Information Theoretic Generalization Bounds for Distributed and Federated Learning

We consider information-theoretic bounds on expected generalization erro...
research
06/30/2021

Non-parametric generalised newsvendor model

In classical newsvendor model, piece-wise linear shortage and excess cos...

Please sign up or login with your details

Forgot password? Click here to reset