Group theoretical methods in machine learning

By Tony Jebara, Imre Kondor. 2008

123 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Equivariance Through Parameter-Sharing (2017, neutral): “to show that parameter-sharing can be used to achieve equivariance to any discrete group action. Application of group theory in machine learning has been the topic of various works in the past (e.g. ,Kondor 2008; Bartok et al.´ ,2010). In particular, many probabilistic inference techniques have been”
Avoiding pathologies in very deep networks (2014, background): “Such feature maps can capture rich structure (Duvenaud et al., 2013), and can enable many types of generalization, such as translation and rotation invariance in images (Kondor, 2008).”
Permutation Equivariant Models for Compositional Generalization in Language (2020, background): “However, as demonstrated by Kondor & Trivedi (2018); Bloem-Reddy & Teh (2019), the above form is very general and subsumes most alternatives.”
Convolutional Gaussian Processes (2017, methodology): “rm can be computed using one-dimensional quadrature. The form of the ELBO means that stochastic optimization using minibatches is applicable. A full discussion of the methodology is given by Matthews [19] . We optimise the ELBO instead of the marginal likelihood to nd the hyperparameters. 2.2 Inter-”
A Group-Theoretic Approach to Abstraction: Hierarchical, Interpretable, and Task-Free Clustering (2018, result): “This is contrary to much prior work at the intersection of group theory and learning (Kondor, 2008) that often encodes domain-relevant symmetries in features or kernels rather than learns them as new ﬁndings.”
Deep Symmetry Networks (2014, background): “A few applications are discussed by Kondor [12], and they are also used in determinantal point processes [14].”