# Learning How to Strategically Disclose Information

arXiv: https://arxiv.org/abs/2403.08741 · HTML: https://mlsanity.com/paper/2403.08741/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 13 Mar 2024.

## Builds on (most cited first, 5 of 5)

- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Value of Information in Games with Multiple Strategic Information Providers](https://mlsanity.com/paper/2306.14886/) (2023)
- [Online Local Learning via Semidefinite Programming](https://mlsanity.com/paper/1403.5287/) (2014)
- [Quadratic Multi-Dimensional Signaling Games and Affine Equilibria](https://mlsanity.com/paper/1503.04360/) (2015)
- [Online linear optimization with the log-determinant regularizer](https://mlsanity.com/paper/1710.10002/) (2017)

## Built on by (most cited first, 1 of 1)

- [Adaptive Agent Design](https://mlsanity.com/paper/2609.12486/) (2026)

## Abstract (arXiv)

Strategic information disclosure, in its simplest form, considers a game between an information provider (sender) who has access to some private information that an information receiver is interested in. While the receiver takes an action that affects the utilities of both players, the sender can design information (or modify beliefs) of the receiver through signal commitment, hence posing a Stackelberg game. However, obtaining a Stackelberg equilibrium for this game traditionally requires the sender to have access to the receiver's objective. In this work, we consider an online version of information design where a sender interacts with a receiver of an unknown type who is adversarially chosen at each round. Restricting attention to Gaussian prior and quadratic costs for the sender and the receiver, we show that O(√T) regret is achievable with full information feedback, where T is the total number of interactions between the sender and the receiver. Further, we propose a novel parametrization that allows the sender to achieve O(√T) regret for a general convex utility function. We then consider the Bayesian Persuasion problem with an additional cost term in the objective function, which penalizes signaling policies that are more informative and obtain O(log(T)) regret. Finally, we establish a sublinear regret bound for the partial information feedback setting and provide simulations to support our theoretical results.