Online Nonnegative Matrix Factorization With Robust Stochastic Approximation

By Naiyang Guan, Dacheng Tao, Zhigang Luo, Bo Yuan. IEEE Transactions on Neural Networks and Learning Systems, 2012

301 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/6ba5e90fc9bd0165d9459cd6baa44537a21e2c53

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Dacheng Tao
2. Jiashi Feng
3. Xuelong Li
4. Shuicheng Yan
5. Meng Wang
6. Yi Yang
7. Rongrong Ji
8. Yue Gao

Citations in the corpus

• Incremental learning algorithms and applications (2016, methodology): “Online or incremental learning techniques have also been developed for alternative tasks such as clustering [109, 91], dimensionality reduction [25, 12, 24, 6, 123, 93], feature selection and data representation[179, 59, 42, 173, 27, 72], reinforcement learning [11, 60], mining and inference [54, 12”
• Contextual Bandits with Latent Confounders: An NMF Approach (2016, background): “Online Matrix factorization : The non-negative matrix factorization (NMF) problem has generated a lot of interest in the area of semi-supervised topic modeling.”
• BIDMach: Large-scale Learning with Zero Memory Allocation (2013, background): “g those that use stochastic gradient optimization, “online” or “streaming” implementations [2], [3], and most MCMC implementations.”
• Online Robust PCA via Stochastic Optimization (2013, methodology): “Based on that work, [9] proposes an online nonnegative matrix factorization method.”
• 3-D Object Retrieval and Recognition With Hypergraph Analysis (2012, methodology): “There are many existing nonnegative matrix factorization methods, such as in [50]–[52].”
• Data-intensive applications, challenges, techniques and technologies: A survey on Big Data (2014, methodology): “There are a large number of methods to reduce dimension [147,109,56].”
• Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression (2012, methodology): “In addition, other effective priors, such as edge prior [35], gradient prior [36], and sparse prior [51]–[53] can also be employed to extend the proposed SR framework.”