Sparse coding provides a class of algorithms for finding succinct representations of stimuli; given only unlabeled input data, it discovers basis functions that capture higher-level features in the data. However, finding sparse codes remains a very difficult computational problem. In this paper, we ...
Moitra. Simple, efficient, and neural algorithms for sparse coding. In Proceedings of the Conference on Learning Theory (COLT), 2015.S. Arora, R. Ge, T. Ma, and A. Moitra. Simple, efficient, and neural algorithms for sparse coding. In Proceedings of The 28th Conference on Learning Theory...
This allows us to apply dual optimization, which essentially results in the same linear sparse coding problem in dual variables, highly beneficial compared with the existing methods that suffer from local minima and restricted forms of kernel function. The efficiency of our algorithms is demonstrated ...
Table 1. Time and space complexities of RNA folding algorithms. For SSF variants, n denotes the length of the input string. For SAF, n and m denote the lengths of the two input strings. D(n) stands for the time complexity of computing the distance product of two n× n matrices, where...
Recently, sparse coding based visual tracking (l_1-tracker) has been obtained increasing attention and many relative algorithms are proposed. In the framework of these algorithms, each candidate region is sparsely represented by a set of target templates. However, almost all these algorithms ignore ...
2022-NIPS-Accelerated Projected Gradient Algorithms for Sparsity Constrained Optimization Problems 2022-NIPS-Feature Learning in L2-regularized DNNs: Attraction/Repulsion and Sparsity 2022-NIPS-Learning Best Combination for Efficient N:M Sparsity 2022-NIPS-Accelerating Sparse Convolution with Column Vector-Wise...
Efficient ADMM-based Algorithms for Convolutional Sparse Coding Convolutional sparse coding improves on the standard sparse approximation by incorporating a global shift-invariant model. The most efficient convolutional sparse coding methods are based on the alternating direction method of multiplier... FG ...
Overall, the research proves the efficient coding principle’s effectiveness for unsupervised structure learning, and that the proposed global sparse coding-based structure-learning algorithms can achieve performance comparable with the best human-designed structures. ...
learning algorithms provide a second, implicit constraint on neural coding in addition to the explicit constraint imposed by the limited neural resources. Together, this inspiration from learning theory points to the possibility that effective learning algorithms will naturally produce better representations ...
Sparse projection has been shown to be highly effec- tive in several domains, including image denoising and scene / object classification. However, practical applica- tion to large scale problems such as video analysis requires efficient versions of sparse projection algorithms such as Orthogonal...