conftrace_

deep linear network

34 papers

Explore in graph

Co-occurring keywords · papers mentioning both

gradient descent (9) representation learning (6) gradient flow (5) implicit regularization (5) residual network (4) learning dynamics (4) neural network optimization (4) matrix factorization (4) feature learning (4) saddle point (3)

Papers

Gradient descent aligns the layers of deep linear networks ICLR 2019 Implicit Regularization in Deep Matrix Factorization NeurIPS 2019 On Dropout and Nuclear Norm Regularization ICML 2019 Small nonlinearities in activation functions create bad local minima in neural networks ICLR 2019 Width Provably Matters in Optimization for Deep Linear Neural Networks ICML 2019 Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global ICML 2018 Exact natural gradient in deep linear networks and its application to the nonlinear case NeurIPS 2018 Global Optimality Conditions for Deep Neural Networks ICLR 2018 Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks ICML 2018