https://github.com/code-implementation1/Code1/tree/main/EF-ENAS
ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
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.
ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
Second-Order Stochastic Optimization for Machine Learning in Linear Time
ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning
Optimizing Neural Networks with Kronecker-factored Approximate Curvature
Optimizing Neural Networks with Kronecker-factored Approximate Curvature
Benchopt: Reproducible, efficient and collaborative optimization benchmarks
Averaging Weights Leads to Wider Optima and Better Generalization
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
Generating Tertiary Protein Structures via an Interpretative Variational Autoencoder
Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization
EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learning
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
CoCoA: A General Framework for Communication-Efficient Distributed Optimization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.