skip to main content
Explore Scholarly Publications and Datasets in the NSF-PAR

  • Home
  • Search Results
  • Page 1 of 1

Search for: All records

Creators/Authors contains: "Thomas, Philip"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. ; ; ; ; ; ( , Proceedings of the 10th International Conference on Learning Representations (ICLR))
    Recent studies found that using machine learning for social applications can lead to injustice in the form of racist, sexist, and otherwise unfair and discriminatory outcomes. To address this challenge, recent machine learning algorithms have been designed to limit the likelihood such unfair behavior occurs. However, these approaches typically assume the data used for training is representative of what will be encountered in deployment, which is often untrue. In particular, if certain subgroups of the population become more or less probable in deployment (a phenomenon we call demographic shift), prior work's fairness assurances are often invalid. In this paper, wemore »consider the impact of demographic shift and present a class of algorithms, called Shifty algorithms, that provide high-confidence behavioral guarantees that hold under demographic shift when data from the deployment environment is unavailable during training. Shifty, the first technique of its kind, demonstrates an effective strategy for designing algorithms to overcome demographic shift's challenges. We evaluate Shifty using the UCI Adult Census dataset, as well as a real-world dataset of university entrance exams and subsequent student success. We show that the learned models avoid bias under demographic shift, unlike existing methods. Our experiments demonstrate that our algorithm's high-confidence fairness guarantees are valid in practice and that our algorithm is an effective tool for training models that are fair when demographic shift occurs.« less
    Free, publicly-accessible full text available April 25, 2023
  2. ; ; ( , Proceedings of Machine Learning Research)
    Free, publicly-accessible full text available July 1, 2022
  3. ; ; ; ; ( , Proceedings of Machine Learning Research)
    Free, publicly-accessible full text available July 1, 2022
  4. ; ; ( , Proceedings of the AAAI Conference on Artificial Intelligence)
    Accepted Manuscript Full Text Available
  5. ; ( , Advances in neural information processing systems)
    Accepted Manuscript Full Text Available
  6. ; ; ; ; ( , Advances in neural information processing systems)
    Accepted Manuscript Full Text Available
  7. ; ; ; ; ; ; ( , Advances in neural information processing systems)
    We present RobinHood, an offline contextual bandit algorithm designed to satisfy a broad family of fairness constraints. Our algorithm accepts multiple fairness definitions and allows users to construct their own unique fairness definitions for the problem at hand. We provide a theoretical analysis of RobinHood, which includes a proof that it will not return an unfair solution with probability greater than a user-specified threshold. We validate our algorithm on three applications: a tutoring system in which we conduct a user study and consider multiple unique fairness definitions; a loan approval setting (using the Statlog German credit data set) in whichmore »well-known fairness definitions are applied; and criminal recidivism (using data released by ProPublica). In each setting, our algorithm is able to produce fair policies that achieve performance competitive with other offline and online contextual bandit algorithms.« less
    Accepted Manuscript Full Text Available
  8. ; ; ; ; ; ( , Science)
    Intelligent machines using machine learning algorithms are ubiquitous, ranging from simple data analysis and pattern recognition tools to complex systems that achieve superhuman performance on various tasks. Ensuring that they do not exhibit undesirable behavior—that they do not, for example, cause harm to humans—is therefore a pressing problem. We propose a general and flexible framework for designing machine learning algorithms. This framework simplifies the problem of specifying and regulating undesirable behavior. To show the viability of this framework, we used it to create machine learning algorithms that precluded the dangerous behavior caused by standard machine learning algorithms in our experiments.more »Our framework for designing machine learning algorithms simplifies the safe and responsible application of machine learning.« less
    Full Text Available 
  9. ; ; ; ( , Results in Physics)
    Full Text Available 
  10. ; ; ; ; ; ; ; ; ; ; et al ( , Nature)
    Green plants (Viridiplantae) include around 450,000–500,000 species of great diversity and have important roles in terrestrial and aquatic ecosystems. Here, as part of the One Thousand Plant Transcriptomes Initiative, we sequenced the vegetative transcriptomes of 1,124 species that span the diversity of plants in a broad sense (Archaeplastida), including green plants (Viridiplantae), glaucophytes (Glaucophyta) and red algae (Rhodophyta). Our analysis provides a robust phylogenomic framework for examining the evolution of green plants. Most inferred species relationships are well supported across multiple species tree and supermatrix analyses, but discordance among plastid and nuclear gene trees at a few important nodes highlightsmore »the complexity of plant genome evolution, including polyploidy, periods of rapid speciation, and extinction. Incomplete sorting of ancestral variation, polyploidization and massive expansions of gene families punctuate the evolutionary history of green plants. Notably, we find that large expansions of gene families preceded the origins of green plants, land plants and vascular plants, whereas whole-genome duplications are inferred to have occurred repeatedly throughout the evolution of flowering plants and ferns. The increasing availability of high-quality plant genome sequences and advances in functional genomics are enabling research on genome evolution across the green tree of life.« less
    Full Text Available