A framework to generate sparsity-inducing regularizers for enhanced low-rank matrix completion
Applying half-quadratic optimization to loss functions can yield the corresponding regularizers, while these regularizers are usually not sparsity-inducing regularizers (SIRs). To solve this problem, we devise a framework to generate an SIR with closed-form proximity operator. Besides, we specify our framework using several commonly-used loss functions, and produce the corresponding SIRs, which are then adopted as nonconvex rank surrogates for low-rank matrix completion. Furthermore, algorithms based on the alternating direction method of multipliers are developed. Extensive numerical results show the effectiveness of our methods in terms of recovery performance and runtime.
Code (0)
등록된 구현이 없습니다.
Tasks
Low-Rank Matrix CompletionMatrix CompletionSimilar Papers 제목 키워드 기반
Low-Rank Tensor Completion via Novel Sparsity-Inducing Regularizers
To alleviate the bias generated by the l1-norm in the low-rank tensor completion problem, nonconvex surrogates/regularizers have been suggested to replace the tensor nuclear norm, although both can achieve sparsity. Howe…
Emergence of Implicit Filter Sparsity in Convolutional Neural Networks
We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained using adaptive gradient descent techniques with L2 regulariza…
L2 RegularizationDeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
In seeking for sparse and efficient neural network models, many previous works investigated on enforcing L1 or L0 regularizers to encourage weight sparsity during training. The L0 regularizer measures the parameter spars…
compressed sensingEfficient Neural NetworkPicasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python
We describe a new library named picasso, which implements a unified framework of pathwise coordinate optimization for a variety of sparse learning problems (e.g., sparse linear regression, sparse logistic regression, spa…
regressionSparse LearningAn Extension of Averaged-Operator-Based Algorithms
Many of the algorithms used to solve minimization problems with sparsity-inducing regularizers are generic in the sense that they do not take into account the sparsity of the solution in any particular way. However, algo…