J
Jason D. Lee
Researcher at Princeton University
Publications - 208
Citations - 13130
Jason D. Lee is an academic researcher from Princeton University. The author has contributed to research in topics: Gradient descent & Artificial neural network. The author has an hindex of 56, co-authored 196 publications receiving 10472 citations. Previous affiliations of Jason D. Lee include Stanford University & Kaiser Permanente.
Papers
More filters
Proceedings Article
Gradient descent finds global minima of deep neural networks
TL;DR: This paper showed that gradient descent achieves zero training loss in polynomial time for a deep over-parameterized neural network with residual connections (ResNet) and further extended their analysis to deep residual convolutional neural networks and obtained a similar convergence result.
Journal ArticleDOI
Exact post-selection inference, with application to the lasso
TL;DR: A general approach to valid inference after model selection by the lasso is developed to form valid confidence intervals for the selected coefficients and test whether all relevant variables have been included in the model.
Proceedings Article
Gradient Descent Only Converges to Minimizers
TL;DR: The authors showed that gradient descent converges to a local minimizer almost surely with random initialization by applying the Stable Manifold Theorem from dynamical systems theory, which is proved by applying stable manifold theorem to gradient descent.
Journal ArticleDOI
Theoretical Insights Into the Optimization Landscape of Over-Parameterized Shallow Neural Networks
TL;DR: In this paper, the problem of learning a shallow neural network that best fits a training data set was studied in the over-parameterized regime, where the numbers of observations are fewer than the number of parameters in the model.
Journal ArticleDOI
Ubiquitination-dependent mechanisms regulate synaptic growth and function
Aaron DiAntonio,Ali P. Haghighi,Scott L. Portman,Jason D. Lee,Andrew M. Amaranto,Corey S. Goodman +5 more
TL;DR: It is shown that ubiquitin-dependent mechanisms regulate synaptic development at the Drosophila neuromuscular junction (NMJ) and genetic interactions between fat facets and highwire suggest that synaptic development may be controlled by the balance between positive and negative regulators of ubiquitination.