← Keywords

neural network training

309 papers

Explore in graph

Also known as

DNN NNT

Co-occurring keywords

neural network (6616) neural network optimization (1293) stochastic gradient descent (1088) gradient descent (1143) model compression (3283) deep neural network (1801) stochastic optimization (1060) deep learning (2111) batch normalization (222) non-convex optimization (546)

Papers

Scaled ReLU Matters for Training Vision Transformers AAAI 2022
Locally Adaptive Label Smoothing Improves Predictive Churn ICML 2021
Better Training using Weight-Constrained Stochastic Dynamics ICML 2021
Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision ICML 2021
Towards Understanding Learning in Neural Networks with Linear Teachers ICML 2021
Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization ICML 2021
On the Convergence of Step Decay Step-Size for Stochastic Optimization NIPS 2021
Differentiable Optimization of Generalized Nondecomposable Functions using Linear Programs NIPS 2021
ATP: In-network Aggregation for Multi-tenant Learning NSDI 2021
Efficient Neural Network Training via Forward and Backward Propagation Sparsification NIPS 2021
AC-GC: Lossy Activation Compression with Guaranteed Convergence NIPS 2021
Rethink the Connections among Generalization, Memorization, and the Spectral Bias of DNNs IJCAI 2021
Stochastic Anderson Mixing for Nonconvex Stochastic Optimization NIPS 2021
Improving Deep Learning Interpretability by Saliency Guided Training NIPS 2021
MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents NIPS 2021
How To Train Neural Networks for Flare Removal ICCV 2021
BASE Layers: Simplifying Training of Large, Sparse Models ICML 2021
Deep Frequency Principle Towards Understanding Why Deeper Learning Is Faster AAAI 2021
TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads JMLR 2021
Deterministic Mini-batch Sequencing for Training Deep Neural Networks AAAI 2021
Asynchronous Optimization Methods for Efficient Training of Deep Neural Networks with Guarantees AAAI 2021
Goten: GPU-Outsourcing Trusted Execution of Neural Network Training AAAI 2021
Proof of Learning (PoLe): Empowering Machine Learning with Consensus Building on Blockchains (Demo) AAAI 2021
Fast Certified Robust Training with Short Warmup NIPS 2021
THOR, Trace-based Hardware-driven Layer-Oriented Natural Gradient Descent Computation AAAI 2021