6 accepted papers
The stochastic gradient descent (SGD) is a simple yet very influential algorithm used to find the minimum of a loss (cost) function which is dependent on datasets with large cardinality, such in cases typically associated with deep learning (DL). There exists several variants/improvements over the "…
This paper introduces a convolutional sparse model for anomaly detection in mixed continuous and discrete data. This model, referred to as C-ADDICT, builds upon the experiences of our previous ADDICT algorithm. It can handle discrete and continuous data jointly, is intrinsically shift-invariant, and…
Convolutional sparse representations allow modeling an entire image as an alternative to the more common independent patch-based formulations. Although many approaches have been proposed to efficiently solve the convolutional dictionary learning (CDL) problem, their computational performance is cons…
Mixed norms that promote structured sparsity have broad application in signal processing and machine learning problems. In this work we present a new algorithm for computing the projection onto the l∞,1 ball, which has found application in cognitive neuroscience and classification tasks. This algori…
Existing methods for constructing separable 2D dictionary filter banks approximate a set of K non-separable filters via a linear combination of R ≪ K separable filters. This approach involves the inefficiency of learning an initial set of non-separable filters, and places an upper bound on the quali…
Convolutional sparse representations (CSR) of images are receiving increasing attention as an alternative to the usual independent patch-wise application of standard sparse representations. For CSR the dictionary is a filter bank of non-separable 2D filters, and the representation itself can be view…