arXiv (Cornell University) · 2020 · 28 citations · 44 references
ComputingComputer ScienceMachine LearningStatistical LearningStatistical ModelingDeep LearningDimensionality AssessmentDimensionality ReductionLoss FunctionNeural NetworksParameter EstimationBayesian Deep LearningConvolutional Neural NetworksDescentDimensionality ControlFunctional Diversity AssessmentOverparameterized ModelsParameter Space AnalysisParameter Space Exploration
Neural networks appear to have mysterious generalization properties when using parameter counting as a proxy for complexity. Indeed, neural networks often have many more parameters than there are data points, yet still provide good generalization performance. Moreover, when we measure generalization as a function of parameters, we see double descent behaviour, where the test error decreases, increases, and then again decreases. We show that many of these properties become understandable when viewed through the lens of effective dimensionality, which measures the dimensionality of the parameter space determined by the data. We relate effective dimensionality to posterior contraction in Bayesian deep learning, model selection, width-depth tradeoffs, double descent, and functional diversity in loss surfaces, leading to a richer understanding of the interplay between parameters and functions in deep models. We also show that effective dimensionality compares favourably to alternative norm- and flatness- based generalization measures.
44
Going deeper with convolutions
Christian Szegedy, Wei Liu, Yangqing Jia et al. · 2015 · 46.8K citations
Backpropagation Applied to Handwritten Zip Code Recognition
Yann LeCun, Bernhard E. Boser, J. S. Denker et al. · Neural Computation · 1989 · 11.9K citations
Richard A. Brown, Trevor Hastie, Robert Tibshirani · Biometrics · 1991 · 8.3K citations
J. A. Nelder, R. W. M. Wedderburn · Journal of the Royal Statistical Society Series A (General) · 1972 · 7.2K citations