# Learning to Cooperate in D2D Caching Networks

## TL;DR

This paper introduces an online learning algorithm for D2D caching networks that optimally manages content storage and retrieval, minimizing delivery costs without prior knowledge of request patterns.

## Contribution

It proposes a distributed online gradient descent-based policy that adapts caching decisions in real-time, achieving asymptotic optimality for arbitrary request processes.

## Key findings

- The algorithm effectively reduces delivery costs in simulated D2D networks.
- It operates without prior knowledge of request distributions.
- The policy is scalable and suitable for distributed implementation.

## Abstract

We consider a wireless device-to-device (D2D) cooperative network where memory-endowed nodes store and exchange content. Each node generates random file requests following an unknown and possibly arbitrary spatio-temporal process, and a base station (BS) delivers any file that is not found at its neighbors' cache, at the expense of higher cost. We design an online learning algorithm which minimizes the aggregate delivery cost by assisting each node to decide which files to cache and which files to fetch from the BS and other devices. Our policy relies on the online gradient descent algorithm, is amenable to distributed execution, and achieves asymptotically optimal performance for any request pattern, without prior information.