Stochastic Optimization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 12
- 보존된 평가 기록
- 35
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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/PaddlePaddle/FleetX/blob/develop/examples/resnet/train_fleet_lamb.py
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
https://github.com/PaddlePaddle/FleetX/blob/develop/examples/resnet/train_fleet_static_localsgd.py
Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization
https://github.com/PatriciaRodrigues1994/pytorch-facebook-udacity-challenge
https://github.com/Pingxia/ConvolutionalSketchInversion
https://github.com/ProbabilisticNumerics/probabilistic_line_search
https://github.com/Robinatp/Tensorflow_Model_Inception
https://github.com/Rohit-ChoudharyGit/Train_Fashion_MNIST
https://github.com/SamuelHorvath/Variance_Reduced_Optimizers_Pytorch
Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization
https://github.com/SamuelMarks/doctrans
https://github.com/SdahlSean/RangerOptimizerTensorflow
https://github.com/SevenZhan/Pytorch
https://github.com/ShadenSmith/ghpages-test
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
https://github.com/ShipengWang/HyperAdam
HyperAdam: A Learnable Task-Adaptive Adam for Network Training
https://github.com/ShipengWang/HyperAdam-Tensorflow
HyperAdam: A Learnable Task-Adaptive Adam for Network Training
https://github.com/Sirius79/acGAN
https://github.com/Sj-Amani/Practical_Behavioral_Cloning
https://github.com/Smerity/pytorch-lamb
Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
https://github.com/SnDehghani/pcgrl_d_m
https://github.com/Songlielie/DKT-Plus
https://github.com/SsnL/moco
https://github.com/SsnL/moco_align_uniform
https://github.com/StevenGerrad/large-scale-Evolution-Net
https://github.com/SyneRBI/PETRIC-MaGeZ
https://github.com/Taichi-Yoshikawa/NeuralNetwork
https://github.com/TezRomacH/layer-to-layer-pytorch
Training Large Neural Networks with Constant Memory using a New Execution Algorithm
https://github.com/Thrandis/EKFAC-pytorch
Optimizing Neural Networks with Kronecker-factored Approximate Curvature
https://github.com/TimRoith/BregmanLearning
https://github.com/Tony-Y/pytorch_warmup
https://github.com/TsingZ0/PFL-Non-IID
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
https://github.com/UnofficialJuliaMirror/DeterminantalPointProcesses.jl-9d4a7304-c3b4-5347-99a8-9cc862165b3e
https://github.com/UnofficialJuliaMirrorSnapshots/DeterminantalPointProcesses.jl-9d4a7304-c3b4-5347-99a8-9cc862165b3e
https://github.com/VAZaytsev/QITE
https://github.com/VeritasXu/FDD-MOEA
A Federated Data-Driven Evolutionary Algorithm for Expensive Multi/Many-objective Optimization
https://github.com/WayneDW/Contour-Stochastic-Gradient-Langevin-Dynamics
Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning
https://github.com/XAI-liacs/BLADE
ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.