← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks ICML 2020
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis ICML 2020
The Implicit and Explicit Regularization Effects of Dropout ICML 2020
Maximum-and-Concatenation Networks ICML 2020
Rethinking Bias-Variance Trade-off for Generalization of Neural Networks ICML 2020
Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection ICML 2020
Is the Skip Connection Provable to Reform the Neural Network Loss Landscape? IJCAI 2020
Learning Model with Error -- Exposing the Hidden Model of BAYHENN IJCAI 2020
Information-Theoretic Understanding of Population Risk Improvement with Model Compression AAAI 2020
Generalization Error Bounds of Gradient Descent for Learning Over-Parameterized Deep ReLU Networks AAAI 2020
The HSIC Bottleneck: Deep Learning without Back-Propagation AAAI 2020
New Interpretations of Normalization Methods in Deep Learning AAAI 2020
Estimating Stochastic Linear Combination of Non-Linear Regressions AAAI 2020
Reverse Engineering Configurations of Neural Text Generation Models ACL 2020
Information-Theoretic Probing with Minimum Description Length EMNLP 2020
Robust Design of Deep Neural Networks Against Adversarial Attacks Based on Lyapunov Theory CVPR 2020
Effectively Unbiased FID and Inception Score and Where to Find Them CVPR 2020
Attribution in Scale and Space CVPR 2020
On the Regularization Properties of Structured Dropout CVPR 2020
On Translation Invariance in CNNs: Convolutional Layers Can Exploit Absolute Spatial Location CVPR 2020
Dataless Model Selection With the Deep Frame Potential CVPR 2020
Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks NIPS 2020
DNNs as Layers of Cooperating Classifiers AAAI 2020
Empirical Bounds on Linear Regions of Deep Rectifier Networks AAAI 2020
Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families AAAI 2020