ML Platform Meetup: Infra for Contextual Bandits and Reinforcement Learning
Infrastructure for Contextual Bandits and Reinforcement Learning — theme of the ML Platform meetup hosted at Netflix, Los Gatos on Sep 12, 2019. Contextual and Multi-armed Bandits enable faster and adaptive alternatives to traditional A/B Testing. They enable rapid learning and better decision-making for product rollouts. Broadly speaking, these approaches can be seen as a stepping stone to full-o
MobileLab: Prevent mobile performance regressions - Facebook Code
MobileLab: Highly accurate testing to prevent mobile performance regressions Early in our mobile optimization efforts, each fix meant big leaps in performance improvement. Today, our apps are optimized so much that our time is best spent preventing tiny regressions that, if shipped, could cause our progress to backslide. At Facebook’s scale, that means checking thousands of commits per day to find
Efficient tuning of online systems using Bayesian optimization – Facebook Research
Facebookで投稿や写真などをチェックできます。
People and Cookies: Imperfect Treatment Assignment in Online Experiments - Meta Research | Meta Research
People and Cookies: Imperfect Treatment Assignment in Online ExperimentsWWW 2016 Identifying the same internet user across devices or over time is often infeasible. This presents a problem for online experiments, as it precludes person-level randomization. Randomization must instead be done using imperfect proxies for people, like cookies, email addresses or device identifiers. Cookies present a u
VIDEOS: Facebook’s @Scale 2014, Data Track
VIDEOS: Facebook’s @Scale 2014, Data Track Facebook held its @Scale 2014 conference in San Francisco Sept. 15, and engineering manager Sambavi Muthukrishnan shared videos from the event’s data track in a post on the Facebook engineering blog. Facebook held its @Scale 2014 conference in San Francisco Sept. 15, and engineering manager Sambavi Muthukrishnan shared videos from the event’s data track i
PlanOut | A framework for online field experiments
Focus on parameters PlanOut provides randomized parameter values to Internet services. Instead of using constants for user interface elements or switches controlling the rollout of a new feature or ranking model, just use PlanOut to determine the value of these parameters. Now you have an experiment. Simple or complex It is easy to implement simple A/B tests in PlanOut. But it's also not much hard
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
http://eytan.github.io/benchmarking.pdf
Uncertainty in Online Experiments with Dependent Data: An Evaluation of Bootstrap Methods
このページを見るには、ログインまたは登録してください
https://hci.stanford.edu/publications/2014/planout/planout-www2014.pdf