https://github.com/liuqiangict/lamb_optimizer
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Stochastic Optimization is the task of optimizing certain objective functional by generating and using stochastic random variables. Usually the Stochastic Optimization is an iterative process of generating random variables that progressively finds out the minima or the maxima of the objective functional. Stochastic Optimization is usually applied in the non-convex functional spaces where the usual deterministic optimization such as linear or quadratic programming or their variants cannot be used.
Source: ASOC: An Adaptive Parameter-free Stochastic Optimization Techinique for Continuous Variables
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
Stochastic Hyperparameter Optimization through Hypernetworks
Limited-Memory Matrix Adaptation for Large Scale Black-box Optimization
Optimizing Neural Networks with Kronecker-factored Approximate Curvature
GenAttack: Practical Black-box Attacks with Gradient-Free Optimization
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
Optimizing Neural Networks with Kronecker-factored Approximate Curvature
Quality-Diversity Optimization: a novel branch of stochastic optimization
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning
Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.