6.9k citations
- IBM (United States)US632 papers
- Massachusetts Institute of TechnologyUS81 papers
- California Institute of TechnologyUS78 papers
- Vassar CollegeUS72 papers
- Centre National de la Recherche ScientifiqueFR48 papers
- University of Illinois Urbana-ChampaignUS48 papers
- Space Telescope Science InstituteUS46 papers
- IBM Research - AlmadenUS42 papers
- Instituto de Astrofísica de CanariasES42 papers
- Columbia UniversityUS41 papers
- Max Planck Institute for AstronomyDE38 papers
- Universidad de La LagunaES38 papers
8 papers · 2 filters
CuMF_SGD: Fast and Scalable Matrix Factorization
Xiaolong Xie, Wei Tan, Liana L. Fong +1
Matrix factorization (MF) has been widely used in e.g., recommender systems, topic modeling and word embedding. Stochastic gradient descent (SGD) is popular in solving MF problems…
DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
Shuochao Yao, Shaohan Hu, Yiran Zhao +2
Mobile sensing applications usually require time-series inputs from sensors. Some applications, such as tracking, can use sensed acceleration and rate of rotation to calculate disp…
Doubly Convolutional Neural Networks
Shuangfei Zhai, Yu Cheng, Weining Lu +1
Building large models with parameter sharing accounts for most of the success of deep convolutional neural networks (CNNs). In this paper, we propose doubly convolutional neural ne…
Deep Structured Energy Based Models for Anomaly Detection
Shuangfei Zhai, Yu Cheng, Weining Lu +1
In this paper, we attack the anomaly detection problem by directly modeling the data distribution with deep architectures. We propose deep structured energy based models (DSEBMs),…
Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradient
Tianbao Yang, Lijun Zhang, Rong Jin +1
This work focuses on dynamic regret of online convex optimization that compares the performance of online learning to a clairvoyant who knows the sequence of loss functions in adva…
Some Insights into the Geometry and Training of Neural Networks
Ewout van den Berg
Neural networks have been successfully used for classification tasks in a rapidly growing number of practical applications. Despite their popularity and widespread use, there are s…