10.9k citations
- Centre National de la Recherche ScientifiqueFR604 papers
- University of ChicagoUS559 papers
- Université Paris CitéFR558 papers
- Columbia UniversityUS551 papers
- Lawrence Berkeley National LaboratoryUS533 papers
- Tel Aviv UniversityIL531 papers
- Brookhaven National LaboratoryUS527 papers
- The Ohio State UniversityUS526 papers
- University of OxfordGB526 papers
- University of California, Santa CruzUS525 papers
- University of CambridgeGB523 papers
- Sorbonne UniversitéFR521 papers
7 papers · 2 filters
Imitation Learning via Off-Policy Distribution Matching
Ilya Kostrikov, Ofir Nachum, Jonathan Tompson
When performing imitation learning from expert demonstrations, distribution matching is a popular approach, in which one alternates between estimating distribution ratios and then…
E.T.-RNN: Applying Deep Learning to Credit Loan Applications
Dmitrii Babaev, Maxim Savchenko, Alexander Tuzhilin +1
In this paper we present a novel approach to credit scoring of retail customers in the banking industry based on deep learning methods. We used RNNs on fine grained transnational d…
Function-Space Distributions over Kernels
Gregory W. Benton, Wesley J. Maddox, Jayson P. Salkey +2
Gaussian processes are flexible function approximators, with inductive biases controlled by a covariance kernel. Learning the kernel is the key to representation learning and stron…
Visus: An Interactive System for Automatic Machine Learning Model Building and Curation
Aécio Santos, Sonia Castelo, Cristian Felix +6
While the demand for machine learning (ML) applications is booming, there is a scarcity of data scientists capable of building such models. Automatic machine learning (AutoML) appr…
Reproducibility in Machine Learning for Health
Matthew B. A. McDermott, Shirly Wang, Nikki Marinsek +3
Machine learning algorithms designed to characterize, monitor, and intervene on human health (ML4H) are expected to perform safely and reliably when operating at scale, potentially…
SWALP : Stochastic Weight Averaging in Low-Precision Training
Guandao Yang, Tianyi Zhang, Polina Kirichenko +3
Low precision operations can provide scalability, memory savings, portability, and energy efficiency. This paper proposes SWALP, an approach to low precision training that averages…