TL;DR
This approach breaks through the exploration-exploitation trade-off bottleneck, delivering an efficient solution for recommender system cold-start scenarios.
Best Arm Identification (BAI) conventionally measures the cost of experimentation by the number of samples collected. In many operational settings, however, the cost of exploration relative to a trusted baseline already in place is equally important. We study BAI under both a fixed sampling horizon and a regret budget....
The results show that the SPADE metric successfully prevents algorithms from exploiting beyond-accuracy measures with irrelevant or non-personalized recommendations, reliably isolating serendipitous discoveries.
This review systematically examines two types of algorithms: passive methods (e.g., sliding-window UCB, discounted UCB), which filter out outdated data’s interference through forgetting mechanisms; and active methods (e.g., TS-CD, R-BOCPD), which dynamically update their parameters by detecting changes.
GRPO assigns the same group-relative advantage to equally rewarded responses within a question, leaving their generation uncertainty unused. We introduce MGE-PO, centered on four-quadrant (4Q) advantage shaping that combines verified correctness with rollout generation entropy. Correctness determines the sign of an add...
. Multi-armed bandit (MAB) algorithms are commonly used in sequential decision tasks such as online recommendation and advertising. In real-world systems, algorithms often have limited time and data to learn from, and poor decisions can be costly. From a finite-horizon perspective, this paper presents a mechanism-level...
Historically, recommendation systems have focused on maximizing precision by treating user preference as a static, predictable target. However, this approach ignores both the inherent randomness of human behavior and the model’s own varying levels of confidence. To compensate, many industrial systems rely on "reserved...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
