147 citations
- Carnegie Mellon UniversityUS4 papers
- Johns Hopkins UniversityUS3 papers
- Amazon (United States)US2 papers
- The University of AdelaideAU2 papers
- Toyota Technological Institute at ChicagoUS2 papers
- Allen (United States)US1 paper
- Apple (Germany)DE1 paper
- Australian Centre for Robotic VisionAU1 paper
- Colorado State UniversityUS1 paper
- DELL (United States)US1 paper
- Duke UniversityUS1 paper
- Georgetown UniversityUS1 paper
17 papers · 1 filter
Asymmetric Random Projections
Nick Ryder, Zohar Karnin, Edo Liberty
Random projections (RP) are a popular tool for reducing dimensionality while preserving local geometry. In many applications the data set to be projected is given to us in advance,…
Generating Diverse and Informative Natural Language Fashion Feedback
Gil Sadeh, Lior Fritz, Gabi Shalev +1
Recent advances in multi-modal vision and language tasks enable a new set of applications. In this paper, we consider the task of generating natural language fashion feedback on ou…
Discrepancy, Coresets, and Sketches in Machine Learning
Zohar Karnin, Edo Liberty
This paper defines the notion of class discrepancy for families of functions. It shows that low discrepancy classes admit small offline and streaming coresets. We provide general t…
DiffQue: Estimating Relative Difficulty of Questions in Community Question Answering Services
Deepak Thukral, Adesh Pandey, Rishabh Gupta +2
Automatic estimation of relative difficulty of a pair of questions is an important and challenging problem in community question answering (CQA) services. There are limited studies…
DARC: Differentiable ARchitecture Compression
Shashank Singh, Ashish Khetan, Zohar Karnin
In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Different…
Learning Compact Neural Networks Using Ordinary Differential Equations as Activation Functions
MohamadAli Torkamani, Phillip Wallis, Shiv Shankar +1
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential e…