conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3,648 papers

Papers per year

Papers

Bidirectional Learning for Offline Infinite-width Model-based Optimization NIPS 2022
Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime NIPS 2022
RNNs of RNNs: Recursive Construction of Stable Assemblies of Recurrent Neural Networks NIPS 2022
Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach NIPS 2022
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NIPS 2022
Interpreting Operation Selection in Differentiable Architecture Search: A Perspective from Influence-Directed Explanations NIPS 2022
On the Stability and Scalability of Node Perturbation Learning NIPS 2022
Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks NIPS 2022
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias NIPS 2022
A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity NIPS 2022
Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search NIPS 2022
Sobolev Acceleration and Statistical Optimality for Learning Elliptic Equations via Gradient Descent NIPS 2022
The least-control principle for local learning at equilibrium NIPS 2022
Real-Valued Backpropagation is Unsuitable for Complex-Valued Neural Networks NIPS 2022
Temporal Effective Batch Normalization in Spiking Neural Networks NIPS 2022
On the Double Descent of Random Features Models Trained with SGD NIPS 2022
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis NIPS 2022
SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance NIPS 2022
On the Parameterization and Initialization of Diagonal State Space Models NIPS 2022
Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions NIPS 2022
Global Convergence and Stability of Stochastic Gradient Descent NIPS 2022
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) NIPS 2022
Do Residual Neural Networks discretize Neural Ordinary Differential Equations? NIPS 2022
Revisit last-iterate convergence of mSGD under milder requirement on step size NIPS 2022
Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions NIPS 2022