← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Theoretical Linear Convergence of Unfolded ISTA and Its Practical Weights and Thresholds NIPS 2018
Deep Homogeneous Mixture Models: Representation, Separation, and Approximation NIPS 2018
On the Practical Computational Power of Finite Precision RNNs for Language Recognition ACL 2018
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing ACL 2018
On Neuronal Capacity NIPS 2018
Analytic Expressions for Probabilistic Moments of PL-DNN With Gaussian Input CVPR 2018
How to Start Training: The Effect of Initialization and Architecture NIPS 2018
Computing Higher Order Derivatives of Matrix and Tensor Expressions NIPS 2018
Implicit Bias of Gradient Descent on Linear Convolutional Networks NIPS 2018
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries NIPS 2018
Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice NIPS 2017
Limits of End-to-End Learning ACML 2017
On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017
Nonlinear random matrix theory for deep learning NIPS 2017
How regularization affects the critical points in linear networks NIPS 2017
The Expressive Power of Neural Networks: A View from the Width NIPS 2017
Invariance and Stability of Deep Convolutional Representations NIPS 2017
Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data NIPS 2017
The Numerics of GANs NIPS 2017
SGD Learns the Conjugate Kernel Class of the Network NIPS 2017
Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks NIPS 2017
On the Learnability of Fully-Connected Neural Networks AISTATS 2017
Deep Hyperspherical Learning NIPS 2017
Implicit Regularization in Matrix Factorization NIPS 2017
SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud NIPS 2017