14.3k citations
- University of MinnesotaUS138 papers
- University of Minnesota SystemUS20 papers
- California Institute of TechnologyUS14 papers
- University of California, BerkeleyUS10 papers
- Goddard Space Flight CenterUS7 papers
- University of California, IrvineUS7 papers
- University of California, Santa CruzUS7 papers
- Jet Propulsion LaboratoryUS6 papers
- Pennsylvania State UniversityUS6 papers
- Syracuse UniversityUS6 papers
- The Ohio State UniversityUS6 papers
- Columbia UniversityUS5 papers
11 papers · 1 filter
ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
Xiangyi Chen, Sijia Liu, Kaidi Xu +4
The adaptive momentum method (AdaMM), which uses past gradients to update descent directions and learning rates simultaneously, has become one of the most popular first-order optim…
Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond
Arindam Banerjee, Qilong Gu, Vidyashankar Sivakumar +1
Several important families of computational and statistical results in machine learning and randomized algorithms rely on uniform bounds on quadratic forms of random vectors or mat…
Structured Dictionary Learning for Energy Disaggregation
Shalini Pandey, George Karypis
The increased awareness regarding the impact of energy consumption on the environment has led to an increased focus on reducing energy consumption. Feedback on the appliance level…
Stability and Generalization of Graph Convolutional Neural Networks
Saurabh Verma, Zhi-Li Zhang
Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have show…
Text segmentation on multilabel documents: A distant-supervised approach
Saurav Manchanda, George Karypis
Segmenting text into semantically coherent segments is an important task with applications in information retrieval and text summarization. Developing accurate topical segmentation…
Distributed representation of multi-sense words: A loss-driven approach
Saurav Manchanda, George Karypis
Word2Vec's Skip Gram model is the current state-of-the-art approach for estimating the distributed representation of words. However, it assumes a single vector per word, which is n…