Differentiable Sparse Coding

By J. Bagnell, David M. Bradley. 2008

113 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Optimization & Training

How researchers see this paper

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

In Representation & Self-Supervised Learning

In Optimization & Training

Citations in the corpus

Representation Learning: A Review and New Perspectives (2012, methodology): “There are numerous examples of its successful application as a feature representation scheme, including natural image modeling (Raina et al., 2007; Kavukcuoglu et al., 2008; Coates and Ng, 2011a; Yu et al., 2011), audio classification (Grosse et al., 2007), NLP (Bagnell and Bradley, 2009), as well a”
Practical Recommendations for Gradient-Based Training of Deep Architectures (2012, methodology): “A common practice in the Deep Learning literature (Ranzato et al., 2007, 2008b; Lee et al., 2008, 2009; Bagnell and Bradley, 2009; Glorot et al., 2011a; Coates and Ng, 2011; Goodfellow et al., 2011) consists in adding a penalty term to the training criterion that encourages the hidden units to be sp”
Deep Learning of Representations: Looking Forward (2013, background): “An even more radically different solution to the problem of avoiding explicit latent variables was recently introduced in Bengio et al. (2013c) and Bengio and Thibodeau-Laufer (2013).”
Online Learning for Matrix Factorization and Sparse Coding (2009, neutral): “Note also that convex smooth approximation of sparse regularizers (Bradley and Bagnell, 2009), or structured sparsity-inducing regularizers (Jenatton et al.”
Large-scale deep unsupervised learning using graphics processors (2009, background): “Such a higher-level representation can then be applied to classi.cation tasks, where it leads to good results even with limited labeled data (Raina et al., 2007; Bradley & Bagnell, 2008).”
Task-Driven Dictionary Learning (2010, methodology): “[9], and Bradley and Bagnell [10] have shown that better results can be achieved when the dictionary is obtained in a fully supervised setting, tuned for the prediction task.”
Proximal Methods for Hierarchical Sparse Coding (2010, background): “An interesting common line of research to pursue could be the supervised design of dictionaries, which has been proved useful in the two frameworks (Mairal et al., 2009a; Bradley and Bagnell, 2009; Blei and McAuliffe, 2008).”
Learning Deep Architectures for AI (2007, methodology): “In [6, 121] the task of training the decoder bases in a sparse coding system is coupled with a task of training a classifier on to of the sparse codes.”
Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives (2012, background): “…coding criterion, which are highly non-smooth or even non-differentiable, a problem that motivated other approaches to smooth the inferred codes of sparse coding (Bagnell and Bradley, 2009), so a sparse coding stage could be jointly optimized along with following stages of a deep architecture.”
Energy Disaggregation via Discriminative Sparse Coding (2010, background): “Alternatively, other met hods (though in a different context from disaggregation) have been proposed that use a differentiab le objective function and implicit differentiation to explicitly model the derivative of the activat ions with respect to the basis functions [4]; however, this formulation lo”