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

The alignment property of SGD noise and how it helps select flat minima: A stability analysis NIPS 2022
Fast and Efficient Restoration of Extremely Dark Light Fields WACV 2022
Reflash Dropout in Image Super-Resolution CVPR 2022
Smooth Maximum Unit: Smooth Activation Function for Deep Networks Using Smoothing Maximum Technique CVPR 2022
Exploiting Explainable Metrics for Augmented SGD CVPR 2022
Fire Together Wire Together: A Dynamic Pruning Approach With Self-Supervised Mask Prediction CVPR 2022
Accelerating DETR Convergence via Semantic-Aligned Matching CVPR 2022
A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks NIPS 2022
Transformers from an Optimization Perspective NIPS 2022
Robust High-Resolution Video Matting With Temporal Guidance WACV 2022
Annihilation of Spurious Minima in Two-Layer ReLU Networks NIPS 2022
A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases NIPS 2022
Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis NIPS 2022
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models EMNLP 2022
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token EMNLP 2022
The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains EMNLP 2022
Efficient Hyper-parameter Search for Knowledge Graph Embedding ACL 2022
In Defense of the Unitary Scalarization for Deep Multi-Task Learning NIPS 2022
Adam Can Converge Without Any Modification On Update Rules NIPS 2022
A Combinatorial Perspective on the Optimization of Shallow ReLU Networks NIPS 2022
Efficient Non-Parametric Optimizer Search for Diverse Tasks NIPS 2022
Staged Training for Transformer Language Models ICML 2022
NeuroSchedule: A Novel Effective GNN-based Scheduling Method for High-level Synthesis NIPS 2022
Structural Pruning via Latency-Saliency Knapsack NIPS 2022
What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us? ICML 2022