10.9k citations
- University of PennsylvaniaUS377 papers
- University of MichiganUS93 papers
- University of ChicagoUS91 papers
- University College LondonGB90 papers
- University of OxfordGB90 papers
- University of Illinois Urbana-ChampaignUS86 papers
- Lawrence Berkeley National LaboratoryUS85 papers
- University of Wisconsin–MadisonUS84 papers
- The Ohio State UniversityUS82 papers
- Yale UniversityUS82 papers
- Argonne National LaboratoryUS80 papers
- Duke UniversityUS80 papers
36 papers · 1 filter
Direct Estimation of Spinal Cobb Angles by Structured Multi-Output Regression
Haoliang Sun, Xiantong Zhen, Chris Bailey +3
The Cobb angle that quantitatively evaluates the spinal curvature plays an important role in the scoliosis diagnosis and treatment. Conventional measurement of these angles suffers…
Robust and Stable Black Box Explanations
Himabindu Lakkaraju, Nino Arsov, Osbert Bastani
As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the…
Does Social Support Expressed in Post Titles Elicit Comments in Online Substance Use Recovery Forums?
Anietie Andy, Sharath Guntuku
Individuals recovering from substance use often seek social support (emotional and informational) on online recovery forums, where they can both write and comment on posts, express…
Development, characterisation, and deployment of the SNO+ liquid scintillator
SNO+ Collaboration, :, M. R. Anderson +223
A liquid scintillator consisting of linear alkylbenzene as the solvent and 2,5-diphenyloxazole as the fluor was developed for the SNO+ experiment. This mixture was chosen as it is…
Sparse sketches with small inversion bias
Michał Dereziński, Zhenyu Liao, Edgar Dobriban +1
For a tall matrix and a random sketching matrix , the sketched estimate of the inverse covariance matrix is typically biased: $E[(\…
DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks
Shiyun Xu, Zhiqi Bu
Recent years have witnessed strong empirical performance of over-parameterized neural networks on various tasks and many advances in the theory, e.g. the universal approximation an…