2.5k citations
- IBM Research - Thomas J. Watson Research CenterUS46 papers
- Massachusetts Institute of TechnologyUS22 papers
- Vassar CollegeUS16 papers
- California Institute of TechnologyUS13 papers
- Columbia UniversityUS12 papers
- Stanford UniversityUS11 papers
- Centre National de la Recherche ScientifiqueFR10 papers
- Carnegie Mellon UniversityUS9 papers
- IBM Research - ZurichCH9 papers
- University of Illinois Urbana-ChampaignUS9 papers
- University of MichiganUS9 papers
- Iowa State UniversityUS8 papers
33 papers · 1 filter
A Comparison of Star-Forming Clumps and Tidal Tails in Local Mergers and High Redshift Galaxies
Debra Meloy Elmegreen, Bruce G. Elmegreen, Bradley C. Whitmore +8
The Clusters, Clumps, Dust, and Gas in Extreme Star-Forming Galaxies (CCDG) survey with the Hubble Space Telescope includes multi-wavelength imaging of 13 galaxies less than 100 Mp…
A Scalable MIP-based Method for Learning Optimal Multivariate Decision Trees
Haoran Zhu, Pavankumar Murali, Dzung T. Phan +2
Several recent publications report advances in training optimal decision trees (ODT) using mixed-integer programs (MIP), due to algorithmic advances in integer programming and a gr…
On Learning Continuous Pairwise Markov Random Fields
Abhin Shah, Devavrat Shah, Gregory W. Wornell
We consider learning a sparse pairwise Markov Random Field (MRF) with continuous-valued variables from i.i.d samples. We adapt the algorithm of Vuffray et al. (2019) to this settin…
Understanding the Role of Individual Units in a Deep Neural Network
David Bau, Jun-Yan Zhu, Hendrik Strobelt +3
Deep neural networks excel at finding hierarchical representations that solve complex tasks over large data sets. How can we humans understand these learned representations? In thi…
Active Learning++: Incorporating Annotator's Rationale using Local Model Explanation
Bhavya Ghai, Q. Vera Liao, Yunfeng Zhang +1
We propose a new active learning (AL) framework, Active Learning++, which can utilize an annotator's labels as well as its rationale. Annotators can provide their rationale for cho…
Efficient Orchestration of Host and Remote Shared Memory for Memory Intensive Workloads
Juhyun Bae, Gong Su, Arun Iyengar +2
Since very few contributions to the development of an unified memory orchestration framework for efficient management of both host and remote idle memory have been made, we present…