English
Related papers

Related papers: Effect Size Estimation for Duration Recommendation…

200 papers

Randomized experiments, or A/B tests are used to estimate the causal impact of a feature on the behavior of users by creating two parallel universes in which members are simultaneously assigned to treatment and control. However, in social…

Social and Information Networks · Computer Science 2019-02-20 Craig Tutterow , Guillaume Saint-Jacques

Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the…

Machine Learning · Statistics 2018-08-06 Zi Wang , Stefanie Jegelka

We consider the estimation of heterogeneous treatment effects with arbitrary machine learning methods in the presence of unobserved confounders with the aid of a valid instrument. Such settings arise in A/B tests with an intent-to-treat…

Econometrics · Economics 2019-06-07 Vasilis Syrgkanis , Victor Lei , Miruna Oprescu , Maggie Hei , Keith Battocchi , Greg Lewis

With recent rapid growth in online shopping, AI-powered Engagement Surfaces (ES) have become ubiquitous across retail services. These engagement surfaces perform an increasing range of functions, including recommending new products for…

We study empirical Bayes estimation of the effect sizes of $N$ units from $K$ noisy observations on each unit. We show that it is possible to achieve near-Bayes optimal mean squared error, without any assumptions or knowledge about the…

Methodology · Statistics 2021-08-11 Nikolaos Ignatiadis , Sujayam Saha , Dennis L. Sun , Omkar Muralidharan

Adaptive designs(AD) are a broad class of trial designs that allow preplanned modifications based on patient data providing improved efficiency and flexibility. However, a delay in observing the primary outcome variable can harm this added…

Methodology · Statistics 2025-09-26 Aritra Mukherjee , Michael J. Grayling , James M. S. Wason

Online controlled experiments are the primary tool for measuring the causal impact of product changes in digital businesses. It is increasingly common for digital products and services to interact with customers in a personalised way. Using…

Methodology · Statistics 2021-07-02 C. H. Bryan Liu , Benjamin Paul Chamberlain

The evaluation of recommendation systems is a complex task. The offline and online evaluation metrics for recommender systems are ambiguous in their true objectives. The majority of recently published papers benchmark their methods using…

Information Retrieval · Computer Science 2023-08-15 Petr Kasalický , Rodrigo Alves , Pavel Kordík

Data-driven algorithm selection is a powerful approach for choosing effective heuristics for computational problems. It operates by evaluating a set of candidate algorithms on a collection of representative training instances and selecting…

Machine Learning · Computer Science 2025-12-04 Vaggos Chatziafratis , Ishani Karmarkar , Yingxi Li , Ellen Vitercik

To quantify the progress in development of algorithms and forcefields used in molecular simulations, a method for the assessment of the sampling quality is needed. We propose a general method to assess the sampling quality through the…

Computational Physics · Physics 2010-02-22 Xin Zhang , Divesh Bhatt , Daniel M. Zuckerman

The use of Bayesian information criterion (BIC) in the model selection procedure is under the assumption that the observations are independent and identically distributed (i.i.d.). However, in practice, we do not always have i.i.d. samples.…

Applications · Statistics 2021-05-03 Nan Shen , Bárbara González

Online experimentation platforms collect user feedback at low cost and large scale. Some systems even support real-time or near real-time data processing, and can update metrics and statistics continuously. Many commonly used metrics, such…

Applications · Statistics 2022-11-01 Alex Deng , Michelle Du , Anna Matlin

Models often need to be constrained to a certain size for them to be considered interpretable. For example, a decision tree of depth 5 is much easier to understand than one of depth 50. Limiting model size, however, often reduces accuracy.…

Machine Learning · Computer Science 2020-07-02 Abhishek Ghose , Balaraman Ravindran

The analysis of screening experiments is often done in two stages, starting with factor selection via an analysis under a main effects model. The success of this first stage is influenced by three components: (1) main effect estimators'…

Methodology · Statistics 2024-03-19 Jonathan W. Stallrich , Michael McKibben

Suppose an online platform wants to compare a treatment and control policy, e.g., two different matching algorithms in a ridesharing system, or two different inventory management algorithms in an online retail site. Standard randomized…

Methodology · Statistics 2022-12-27 Peter Glynn , Ramesh Johari , Mohammad Rasouli

Estimation of software reliability often poses a considerable challenge, particularly for critical softwares. Several methods of estimation of reliability of software are already available in the literature. But, so far almost nobody used…

Software Engineering · Computer Science 2024-06-10 Pallabi Ghosh , Ashis Kr. Chakraborty , Soumen Dey

The design of an experiment can be always be considered at least implicitly Bayesian, with prior knowledge used informally to aid decisions such as the variables to be studied and the choice of a plausible relationship between the…

Methodology · Statistics 2017-01-03 David C. Woods , Antony M. Overstall , Maria Adamou , Timothy W. Waite

The challenge of optimal design of experiments (DOE) pervades materials science, physics, chemistry, and biology. Bayesian optimization has been used to address this challenge in vast sample spaces, although it requires framing experimental…

Questions of `how best to acquire data' are essential to modeling and prediction in the natural and social sciences, engineering applications, and beyond. Optimal experimental design (OED) formalizes these questions and creates…

Methodology · Statistics 2026-05-01 Xun Huan , Jayanth Jagalur , Youssef Marzouk

Group sequential designs drive innovation in clinical, industrial, and corporate settings. Early stopping for failure in sequential designs conserves experimental resources, whereas early stopping for success accelerates access to improved…

Methodology · Statistics 2025-11-27 Luke Hagar , Shirin Golchi , Marina B. Klein