Adaptive Caching in the YouTube Content Distribution Network: A Revealed Preference Game-Theoretic Learning Approach
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Cognitive systems are dynamical systems that adapt their behavior to achieve sophisticated outcomes in nonstationary environments. This paper considers two cognitive aspects regarding the problem of distributed caching with limited capacity in a content distribution network that serves YouTube users with multiple edge servers: first, the theory of revealed preference from microeconomics is used to estimate human utility maximization behavior. In particular, a nonparametric learning algorithm is provided to estimate the request probability of YouTube videos from past user behavior. Second, using these estimated request probabilities, the adaptive caching problem is formulated as a noncooperative repeated game in which servers autonomously decide, which videos to cache. The utility function tradesoff the placement cost for caching videos locally with the latency cost associated with delivering the video to the users from a neighboring server. The game is nonstationary as the preferences of users in each region evolve over time. We then propose an adaptive popularity-based video caching algorithm that has two timescales: The slow timescale corresponds to learning user preferences, whereas the fast timescale is a regret-matching algorithm that provides individual servers with caching prescriptions. It is shown that, if all servers follow simple regret minimization for caching, their global behavior is sophisticated—the network achieves a correlated equilibrium, which means that servers can coordinate their caching strategies in a distributed fashion as if there exists a centralized coordinating device that they all trust to follow. In the numerical examples, we use real data from YouTube to illustrate the results.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it