← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Improved Graph Laplacian via Geometric Self-Consistency NIPS 2017
The Marginal Value of Adaptive Gradient Methods in Machine Learning NIPS 2017
Mean Field Residual Networks: On the Edge of Chaos NIPS 2017
An Empirical Study on The Properties of Random Bases for Kernel Methods NIPS 2017
Towards Generalization and Simplicity in Continuous Control NIPS 2017
Train longer, generalize better: closing the generalization gap in large batch training of neural networks NIPS 2017
On the Complexity of Learning Neural Networks NIPS 2017
Convergence Analysis of Two-layer Neural Networks with ReLU Activation NIPS 2017
Spectrally-normalized margin bounds for neural networks NIPS 2017
SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability NIPS 2017
Gradient Descent Can Take Exponential Time to Escape Saddle Points NIPS 2017
Axiomatic Attribution for Deep Networks ICML 2017
Failures of Gradient-Based Deep Learning ICML 2017
On Approximation Guarantees for Greedy Low Rank Optimization ICML 2017
Global Optimality in Neural Network Training CVPR 2017
Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency CVPR 2017
Discrete Deep Feature Extraction: A Theory and New Architectures ICML 2016
Optimal Architectures in a Solvable Model of Deep Networks NIPS 2016
On the Role of Nonlinear Transformations in Deep Neural Network Acoustic Models INTERSPEECH 2016
Deep Learning Games NIPS 2016
Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity NIPS 2016
Orthogonal Random Features NIPS 2016
Residual Networks Behave Like Ensembles of Relatively Shallow Networks NIPS 2016
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods NIPS 2016
Exponential expressivity in deep neural networks through transient chaos NIPS 2016