• Publications
  • Influence
A theory of learning from different domains
TLDR
A classifier-induced divergence measure that can be estimated from finite, unlabeled samples from the domains and shows how to choose the optimal combination of source and target error as a function of the divergence, the sample sizes of both domains, and the complexity of the hypothesis class. Expand
Datasheets for Datasets
TLDR
Datasheets for datasets are proposed, which will facilitate better communication between dataset creators and dataset consumers, and encourage the machine learning community to prioritize transparency and accountability. Expand
Learning Bounds for Domain Adaptation
TLDR
Uniform convergence bounds are given for algorithms that minimize a convex combination of source and target empirical risk in order to adapt a classifier from a source domain with a large amount of training data to different target domain with very little training data. Expand
Manipulating and Measuring Model Interpretability
TLDR
A sequence of pre-registered experiments showed participants functionally identical models that varied only in two factors commonly thought to make machine learning models more or less interpretable: the number of features and the transparency of the model (i.e., whether the model internals are clear or black box). Expand
Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need?
TLDR
This first systematic investigation of commercial product teams' challenges and needs for support in developing fairer ML systems identifies areas of alignment and disconnect between the challenges faced by teams in practice and the solutions proposed in the fair ML research literature. Expand
Run the GAMUT: a comprehensive approach to evaluating game-theoretic algorithms
TLDR
It is shown that there is surprisingly large variation in algorithm performance across different sets of games for two widely-studied problems: computing Nash equilibria and multiagent learning in repeated games. Expand
An optimization-based framework for automated market-making
TLDR
It is proved that any market satisfying a set of intuitive conditions must price securities via a convex cost function, which is constructed via conjugate duality, and that by relaxing the convex hull the authors can gain computational tractability without compromising the market institution's bounded budget. Expand
Online Task Assignment in Crowdsourcing Markets
TLDR
This work presents a two-phase exploration-exploitation assignment algorithm and proves that it is competitive with respect to the optimal offline algorithm which has access to the unknown skill levels of each worker. Expand
Behavioral experiments on biased voting in networks
TLDR
There are well-studied network topologies in which the minority preference consistently wins globally; that the presence of “extremist” individuals, or the awareness of opposing incentives, reliably improve collective performance; and that certain behavioral characteristics of individual subjects, such as “stubbornness,” are strongly correlated with earnings. Expand
Adaptive Task Assignment for Crowdsourced Classification
TLDR
This work investigates the problem of task assignment and label inference for heterogeneous classification tasks and derives a provably near-optimal adaptive assignment algorithm that can lead to more accurate predictions at a lower cost when the available workers are diverse. Expand
...
1
2
3
4
5
...