# Soft-TTL: Time-Varying Fractional Caching

arXiv: https://arxiv.org/abs/1807.03537 · HTML: https://mlsanity.com/paper/1807.03537/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2018.

## Built on by (most cited first, 2 of 2)

- [Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey](https://mlsanity.com/paper/2110.13484/) (2021)
- [Exact Memory-Time Optimization for Prefix-Cached Language Model Serving](https://mlsanity.com/paper/2610.02766/) (2026)

## Abstract (arXiv)

Standard Time-to-Live (TTL) cache management prescribes the storage of entire files, or possibly fractions thereof, for a given amount of time after a request. As a generalization of this approach, this work proposes the storage of a time-varying, diminishing, fraction of a requested file. Accordingly, the cache progressively evicts parts of the file over an interval of time following a request. The strategy, which is referred to as soft-TTL, is justified by the fact that traffic traces are often characterized by arrival processes that display a decreasing, but non-negligible, probability of observing a request as the time elapsed since the last request increases. An optimization-based analysis of soft-TTL is presented, demonstrating the important role played by the hazard function of the inter-arrival request process, which measures the likelihood of observing a request as a function of the time since the most recent request.