← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Understanding the Loss Surface of Neural Networks for Binary Classification ICML 2018
On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups ICML 2018
Convergence guarantees for a class of non-convex and non-smooth optimization problems ICML 2018
Gradient Descent Learns One-hidden-layer CNN: Don’t be Afraid of Spurious Local Minima ICML 2018
Stability and Generalization of Learning Algorithms that Converge to Global Optima ICML 2018
Stronger Generalization Bounds for Deep Nets via a Compression Approach ICML 2018
Spectral Filtering for General Linear Dynamical Systems NIPS 2018
Blind Deconvolutional Phase Retrieval via Convex Programming NIPS 2018
Modern Neural Networks Generalize on Small Data Sets NIPS 2018
How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective NIPS 2018
Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data NIPS 2018
Scaling provable adversarial defenses NIPS 2018
Parameters as interacting particles: long time convergence and asymptotic error scaling of neural networks NIPS 2018
Structured Local Minima in Sparse Blind Deconvolution NIPS 2018
Are ResNets Provably Better than Linear Predictors? NIPS 2018
DeepPINK: reproducible feature selection in deep neural networks NIPS 2018
Efficient Formal Safety Analysis of Neural Networks NIPS 2018
Fast generalization error bound of deep learning from a kernel perspective AISTATS 2018
Towards Provable Learning of Polynomial Neural Networks Using Low-Rank Matrix Estimation AISTATS 2018
The emergence of spectral universality in deep networks AISTATS 2018
Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces NIPS 2018
A Biresolution Spectral Framework for Product Quantization CVPR 2018
An Empirical Evaluation of Sketched SVD and its Application to Leverage Score Ordering ACML 2018
Gradient Estimation with Simultaneous Perturbation and Compressive Sensing JMLR 2018
Visualizing the Loss Landscape of Neural Nets NIPS 2018