Bayesian optimization for policy search via online-offline experimentation
B Letham, E Bakshy - Journal of Machine Learning Research, 2019 - jmlr.org
Online field experiments are the gold-standard way of evaluating changes to real-world
interactive machine learning systems. Yet our ability to explore complex, multi-dimensional …
interactive machine learning systems. Yet our ability to explore complex, multi-dimensional …
Ads allocation in feed via constrained optimization
J Yan, Z Xu, B Tiwana, S Chatterjee - Proceedings of the 26th ACM …, 2020 - dl.acm.org
Social networks and content publishing platforms have newsfeed applications, which show
both organic content to drive engagement, and ads to drive revenue. This paper focuses on …
both organic content to drive engagement, and ads to drive revenue. This paper focuses on …
A methodology for the offline evaluation of recommender systems in a user interface with multiple carousels
N Felicioni, M Ferrari Dacrema… - Adjunct Proceedings of the …, 2021 - dl.acm.org
Many video-on-demand and music streaming services provide the user with a page
consisting of several recommendation lists, ie, widgets or swipeable carousels, each built …
consisting of several recommendation lists, ie, widgets or swipeable carousels, each built …
Page-level optimization of e-commerce item recommendations
The item details page (IDP) is a web page on an e-commerce website that provides
information on a specific product or item listing. Just below the details of the item on this …
information on a specific product or item listing. Just below the details of the item on this …
Email volume optimization at LinkedIn
Online social networking services distribute various types of messages to their members.
Common types of messages include news, connection requests, membership notifications …
Common types of messages include news, connection requests, membership notifications …
Whole page optimization with global constraints
W Ding, D Govindaraj, SVN Vishwanathan - Proceedings of the 25th …, 2019 - dl.acm.org
The Amazon video homepage is the primary gateway for customers looking to explore the
large collection of content, and finding something interesting to watch. Typically, the page is …
large collection of content, and finding something interesting to watch. Typically, the page is …
Measuring the user satisfaction in a recommendation interface with multiple carousels
N Felicioni, M Ferrari Dacrema… - Proceedings of the 2021 …, 2021 - dl.acm.org
It is common for video-on-demand and music streaming services to adopt a user interface
composed of several recommendation lists, ie, widgets or swipeable carousels, each …
composed of several recommendation lists, ie, widgets or swipeable carousels, each …
Ranking with Slot Constraints
Rankings are increasingly used as part of human decision-making processes to most
effectively allocate reviewing resources. Many of these processes have complex constraints …
effectively allocate reviewing resources. Many of these processes have complex constraints …
Recommendation with capacity constraints
In many recommendation settings, the candidate items for recommendation are associated
with a maximum capacity, ie, number of seats in a Point-of-Interest (POI) or number of item …
with a maximum capacity, ie, number of seats in a Point-of-Interest (POI) or number of item …
An efficient combinatorial optimization model using learning-to-rank distillation
Recently, deep reinforcement learning (RL) has proven its feasibility in solving combinatorial
optimization problems (COPs). The learning-to-rank techniques have been studied in the …
optimization problems (COPs). The learning-to-rank techniques have been studied in the …