← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3648 directly classified papers

Papers per year

Papers

Top-KAST: Top-K Always Sparse Training NIPS 2020
The Generalization-Stability Tradeoff In Neural Network Pruning NIPS 2020
How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks? NIPS 2020
On the distance between two neural networks and the stability of learning NIPS 2020
ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks NIPS 2020
Ultra-Low Precision 4-bit Training of Deep Neural Networks NIPS 2020
Self-Distillation Amplifies Regularization in Hilbert Space NIPS 2020
On the training dynamics of deep networks with $L_2$ regularization NIPS 2020
Training Linear Finite-State Machines NIPS 2020
Analytic Characterization of the Hessian in Shallow ReLU Models: A Tale of Symmetry NIPS 2020
A mathematical model for automatic differentiation in machine learning NIPS 2020
Estimating Training Data Influence by Tracing Gradient Descent NIPS 2020
Learning to solve TV regularised problems with unrolled algorithms NIPS 2020
Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization NIPS 2020
Optimal Lottery Tickets via Subset Sum: Logarithmic Over-Parameterization is Sufficient NIPS 2020
Curriculum Learning by Dynamic Instance Hardness NIPS 2020
O(n) Connections are Expressive Enough: Universal Approximability of Sparse Transformers NIPS 2020
STEER : Simple Temporal Regularization For Neural ODE NIPS 2020
Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping NIPS 2020
Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems NIPS 2020
Limits to Depth Efficiencies of Self-Attention NIPS 2020
Fast Transformers with Clustered Attention NIPS 2020
Improving First-Order Optimization Algorithms (Student Abstract) AAAI 2020
Do Subsampled Newton Methods Work for High-Dimensional Data? AAAI 2020
Synchronous Double-channel Recurrent Network for Aspect-Opinion Pair Extraction ACL 2020