conftrace_

neural network optimization

1293 papers

Explore in graph

Co-occurring keywords

model compression (3302) neural network (6616) convolutional neural network (4226) gradient descent (1144) stochastic gradient descent (1091) efficient computing (781) deep neural network (1803) large language model (13587) knowledge distillation (3725) representation learning (6206)

Papers

Towards Efficient and Effective Adversarial Training NIPS 2021
On Monotonic Linear Interpolation of Neural Network Parameters ICML 2021
An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks NIPS 2021
An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models ACL 2021
Implicit Regularization in Tensor Factorization ICML 2021
A Modular Analysis of Provable Acceleration via Polyak’s Momentum: Training a Wide ReLU Network and a Deep Linear Network ICML 2021
GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual Learning EMNLP 2021
Towards Stable and Robust AdderNets NIPS 2021
Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration NIPS 2021
Optimizing Deeper Transformers on Small Datasets ACL 2021
Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation ACL 2021
HAWQ-V3: Dyadic Neural Network Quantization ICML 2021
Stochastic Whitening Batch Normalization CVPR 2021
Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron ACML 2021
BinaryBERT: Pushing the Limit of BERT Quantization ACL 2021
A Universal Law of Robustness via Isoperimetry NIPS 2021
MTAdam: Automatic Balancing of Multiple Training Loss Terms EMNLP 2021
Towards Memory-Efficient Neural Networks via Multi-Level In Situ Generation ICCV 2021
Training Adaptive Computation for Open-Domain Question Answering with Computational Constraints ACL 2021
ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees NIPS 2021
$\alpha$-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression NIPS 2021
Rank & Sort Loss for Object Detection and Instance Segmentation ICCV 2021
A Sliced Wasserstein Loss for Neural Texture Synthesis CVPR 2021
Towards Fast and Accurate Multi-Person Pose Estimation on Mobile Devices IJCAI 2021
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation ICML 2021