Tianjin Province
Technology:
Boosting Adversarial Transferability by Achieving Flat Local Maxima
Specifically, we randomly sample an example and adopt a first-order procedure to approximate the Hessian/vector product, which makes computing more efficient by interpolating two neighboring gradients.
Country:
Technology:
Dynamic Sparsity Is Channel-Level Sparsity Learner Lu Yin 1, Gen Li
Sparse training has received an upsurging interest in machine learning due to its tantalizing saving potential for the entire training process as well as inference.
Country:
- North America > United States > Texas > Travis County > Austin (0.04)
- Europe > Netherlands > North Brabant > Eindhoven (0.04)
- Asia > China > Tianjin Province > Tianjin (0.04)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.68)
Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation
Di Lin is the corresponding author of this paper.
Technology:
Country:
- North America > United States (0.04)
- Asia > China > Tianjin Province > Tianjin (0.04)
Genre:
- Contests & Prizes (0.71)
- Research Report > New Finding (0.48)
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.68)
A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization
Then momentum acceleration is also introduced into our dual accelerating update step.
Country:
- Asia > Middle East > Jordan (0.04)
- Asia > China > Tianjin Province > Tianjin (0.04)
- Asia > China > Shaanxi Province (0.04)
Technology:
A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization
Then momentum acceleration is also introduced into our dual accelerating update step.
Country:
- Asia > Middle East > Jordan (0.05)
- Asia > China > Tianjin Province > Tianjin (0.04)
- Asia > China > Shaanxi Province (0.04)
Technology:
Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training
Surprisingly, we find that most of the studied methods yield similar results.
Country:
- North America > Canada > Ontario > Toronto (0.04)
- Europe > Netherlands > North Brabant > Eindhoven (0.04)
- North America > United States > California > Santa Clara County > Palo Alto (0.04)
- (2 more...)
Genre:
- Research Report > New Finding (1.00)
- Research Report > Experimental Study (0.67)
Technology:
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
- Information Technology > Artificial Intelligence > Vision (0.93)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning (0.67)
Country:
Technology:
- Information Technology > Data Science > Data Mining (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
- Information Technology > Communications (0.73)
- Information Technology > Artificial Intelligence > Machine Learning > Performance Analysis > Accuracy (0.46)