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

Neural Network Optimization

3,648 papers

Papers per year

Papers

Understanding Decoupled and Early Weight Decay AAAI 2021
On the Convergence of Step Decay Step-Size for Stochastic Optimization NIPS 2021
A Deep Conditioning Treatment of Neural Networks ALT 2021
What can linearized neural networks actually say about generalization? NIPS 2021
Argument Pair Extraction via Attention-guided Multi-Layer Multi-Cross Encoding ACL 2021
Local Temperature Scaling for Probability Calibration ICCV 2021
Neural Architecture Search With Random Labels CVPR 2021
LeeBERT: Learned Early Exit for BERT with cross-level optimization ACL 2021
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets ICML 2021
Convergence of adaptive algorithms for constrained weakly convex optimization NIPS 2021
Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network AISTATS 2021
An Improved Single Step Non-Autoregressive Transformer for Automatic Speech Recognition INTERSPEECH 2021
Training Spiking Neural Networks with Accumulated Spiking Flow AAAI 2021
Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift ICCV 2021
On Randomized Classification Layers and Their Implications in Natural Language Generation NAACL 2021
LassoNet: A Neural Network with Feature Sparsity JMLR 2021
Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond NIPS 2021
1-bit Adam: Communication Efficient Large-Scale Training with Adam’s Convergence Speed ICML 2021
Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond NIPS 2021
Adaptive First-Order Methods Revisited: Convex Minimization without Lipschitz Requirements NIPS 2021
Neural Architecture Search as Sparse Supernet AAAI 2021
The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks ICML 2021
Scaled-YOLOv4: Scaling Cross Stage Partial Network CVPR 2021
Hyperparameter Power Impact in Transformer Language Model Training EMNLP 2021
Fractional moment-preserving initialization schemes for training deep neural networks AISTATS 2021