Open AccessJournal Article
Counterfactual reasoning and learning systems: the example of computational advertising
Léon Bottou,Jonas Peters,Joaquin Quiñonero-Candela,Denis X. Charles,D. Max Chickering,Elon Portugaly,Dipankar Ray,Patrice Y. Simard,Ed Snelson +8 more
Reads0
Chats0
TLDR
This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system and allow both humans and algorithms to select the changes that would have improved the system performance.Abstract:
This work shows how to leverage causal inference to understand the behavior of complex learning systems interacting with their environment and predict the consequences of changes to the system. Such predictions allow both humans and algorithms to select the changes that would have improved the system performance. This work is illustrated by experiments on the ad placement system associated with the Bing search engine.read more
Citations
More filters
Posted Content
Concrete Problems in AI Safety
TL;DR: A list of five practical research problems related to accident risk, categorized according to whether the problem originates from having the wrong objective function, an objective function that is too expensive to evaluate frequently, or undesirable behavior during the learning process, are presented.
Posted Content
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
TL;DR: This tutorial article aims to provide the reader with the conceptual tools needed to get started on research on offline reinforcement learning algorithms: reinforcementlearning algorithms that utilize previously collected data, without additional online data collection.
Proceedings Article
Hidden technical debt in Machine learning systems
D. Sculley,Gary Holt,Daniel Golovin,Eugene Davydov,Todd Phillips,Dietmar Ebner,Vinay Chaudhary,Michael Young,Jean-Francois Crespo,Dan Dennison +9 more
TL;DR: It is found it is common to incur massive ongoing maintenance costs in real-world ML systems, and several ML-specific risk factors to account for in system design are explored.
Journal ArticleDOI
Toward Causal Representation Learning
Bernhard Schölkopf,Francesco Locatello,Stefan Bauer,Nan Rosemary Ke,Nal Kalchbrenner,Anirudh Goyal,Yoshua Bengio +6 more
TL;DR: The authors reviewed fundamental concepts of causal inference and related them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research.
Posted Content
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Pang Wei Koh,Shiori Sagawa,Henrik Marklund,Sang Michael Xie,Marvin Zhang,Akshay Balsubramani,Weihua Hu,Michihiro Yasunaga,Richard Lanas Phillips,Irena Gao,Tony Lee,Etienne David,Ian Stavness,Wei Guo,Berton A. Earnshaw,Imran S. Haque,Sara Beery,Jure Leskovec,Anshul Kundaje,Emma Pierson,Sergey Levine,Chelsea Finn,Percy Liang +22 more
TL;DR: WILDS is presented, a benchmark of in-the-wild distribution shifts spanning diverse data modalities and applications, and is hoped to encourage the development of general-purpose methods that are anchored to real-world distribution shifts and that work well across different applications and problem settings.
References
More filters
Book ChapterDOI
Efficient ranking in sponsored search
TL;DR: A sufficient condition under which applying an exponent--strictly less than one--to the quality score improves expected efficiency is provided, and this condition holds for a large class of distributions known as natural exponential families, and for the lognormal distribution.
Posted Content
Sample-efficient Nonstationary Policy Evaluation for Contextual Bandits
TL;DR: This work presents and proves properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators and simultaneously and correctly incorporates techniques from importance weighting, doubly robust evaluation, and nonstationary policy evaluation approaches.
Proceedings Article
Sample-efficient nonstationary policy evaluation for contextual bandits
TL;DR: In this paper, a new offline policy evaluator for exploration learning is presented, which simultaneously and correctly incorporates techniques from importance weighting, doubly robust evaluation, and nonstationary policy evaluation approaches.
Proceedings Article
The do -calculus revisited
TL;DR: This talk surveys the usefulness of the do-calculus in three additional areas: mediation analysis, transportability and metasynthesis and surveys these results with emphasis on the challenges posed by meta-synthesis.