← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Examining the Inductive Bias of Neural Language Models with Artificial Languages ACL 2021
Data and Parameter Scaling Laws for Neural Machine Translation EMNLP 2021
Understanding Model Robustness to User-generated Noisy Texts EMNLP 2021
On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective CVPR 2021
Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing CVPR 2021
Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural Networks CVPR 2021
How Does Topology Influence Gradient Propagation and Model Performance of Deep Networks With DenseNet-Type Skip Connections? CVPR 2021
A Unified Taylor Framework for Revisiting Attribution Methods AAAI 2021
Interpreting Super-Resolution Networks With Local Attribution Maps CVPR 2021
Efficient Certification of Spatial Robustness AAAI 2021
Scalable Verification of Quantized Neural Networks AAAI 2021
On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory AAAI 2021
Frivolous Units: Wider Networks Are Not Really That Wide AAAI 2021
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks AAAI 2021
A Recipe for Global Convergence Guarantee in Deep Neural Networks AAAI 2021
Norm-Based Generalisation Bounds for Deep Multi-Class Convolutional Neural Networks AAAI 2021
Large Norms of CNN Layers Do Not Hurt Adversarial Robustness AAAI 2021
Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability AAAI 2021
A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization AAAI 2021
Right for Better Reasons: Training Differentiable Models by Constraining their Influence Functions AAAI 2021
Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks AAAI 2021
Deep Frequency Principle Towards Understanding Why Deeper Learning Is Faster AAAI 2021
On the Verification of Neural ODEs with Stochastic Guarantees AAAI 2021
A Theoretical Analysis of the Repetition Problem in Text Generation AAAI 2021
On the Softmax Bottleneck of Recurrent Language Models AAAI 2021