scientific article; zbMATH DE number 7306924

MaRDI QIDQ5149042zbMATH OpenFDO

Authors Shuxiao Chen, Edgar Dobriban, J.-H. Lee

Publication date 5 February 2021

Full work available at URL https://arxiv.org/abs/1907.10905, https://jmlr.csail.mit.edu/papers/v21/20-163.html

zbMATH Keywords

data augmentationdeep learningempirical risk minimizationinvariancevariance reduction

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Asymptotically Exact Data Augmentation: Models, Properties, and Algorithms
• A comparison theorem for data augmentation algorithms with applications
• The data augmentation algorithm: theory and methodology
• Estimator augmentation with applications in high-dimensional group inference
• Seeking efficient data augmentation schemes via conditional and marginal augmentation
• Data augmentation via Lévy processes
• Generalised data augmentation and posterior inferences
• A theoretical comparison of the data augmentation, marginal augmentation and PX-DA algorithms
• Improving efficiency of data augmentation algorithms using Peskun's theorem

Cited in

(11)

• Can generalised divergences help for invariant neural networks?
• A Group-Theoretic Framework for Data Augmentation
• Deep learning from a statistical perspective
• Injectivity, stability, and positive definiteness of max filtering
• Randomization tests for conditional group symmetry
• Linear separation capacity of self-supervised representation learning
• SymmPI: predictive inference for data with group symmetries
• Augmentation invariant manifold learning
• Group-invariant max filtering
• PAC-Chernoff bounds: understanding generalization in the interpolation regime
• A unified framework to enforce, discover, and promote symmetry in machine learning

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5149042)