Robust Budget Pacing with a Single Sample
25. července 2023
Řečníci
Rachitesh Kumar
Sprecher:in · 0 Follower:innen
Santiago Balseiro
Sprecher:in · 0 Follower:innen
Vahab Mirrokni
Sprecher:in · 0 Follower:innen
Balasubramanian Sivan
Sprecher:in · 0 Follower:innen
O prezentaci
Major Internet advertising platforms offer budget pacing tools as a standard service for advertisers to manage their ad campaigns. Given the inherent non-stationarity in an advertiser's value and also competing advertisers' values over time, a commonly used approach is to learn a target expenditure plan that specifies a target spend as a function of time, and then run a controller that tracks this plan. This raises the question: *how many historical samples are required to learn a good expenditure plan*? We study this question by considering an advertiser repeatedly participating in $T$ second-price auctions, where the tuple of her value and the highest competing bid is drawn from an unknown time-varying distribution. The advertiser seeks to maximize her total utility subject to her budget constraint. Prior work has shown the sufficiency of *$T\log T$ samples per distribution* to achieve the optimal $O(\sqrt{T})$-regret. We dramatically improve this state-of-the-art and show that *just one sample per distribution* is enough to achieve the near-optimal $\tilde O(\sqrt{T})$-regret, while still being robust to noise in the sampling distributions.Major Internet advertising platforms offer budget pacing tools as a standard service for advertisers to manage their ad campaigns. Given the inherent non-stationarity in an advertiser's value and also competing advertisers' values over time, a commonly used approach is to learn a target expenditure plan that specifies a target spend as a function of time, and then run a controller that tracks this plan. This raises the question: *how many historical samples are required to learn a good expenditu…
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Why does Throwing Away Data Improve Worst-Group Error?
Später ansehen
Is Overfitting Necessary for Implicit Video Representation?
Später ansehen
Hee Min Choi, …
Contextual Conservative Interleaving Bandits
Später ansehen
OCD: Learning to Overfit with Conditional Diffusion Models
Später ansehen
The Future of A.I. for Social Work
Später ansehen
