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/etorarza/rvcompare
공식 코드Comparing Two Samples Through Stochastic Dominance: A Graphical Approach
https://github.com/evolutionary-intelligence/pypop
공식 코드PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization
https://github.com/evoml/evoml
공식 코드https://github.com/eyounx/ZOOpt
공식 코드https://github.com/ezelikman/justonebyte
공식 코드https://github.com/fabian-sp/MoMo
공식 코드https://github.com/facebookresearch/LaMCTS
공식 코드Sample-Efficient Neural Architecture Search by Learning Action Space
https://github.com/facebookresearch/fairscale/blob/main/fairscale/experimental/nn/data_parallel/gossip/distributed.py
공식 코드SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
https://github.com/facebookresearch/madgrad
공식 코드https://github.com/facebookresearch/optimizers/tree/main/distributed_shampoo
공식 코드https://github.com/facebookresearch/qhoptim
공식 코드https://github.com/fcampelo/MOEADr
공식 코드https://github.com/fderoos/probabilistic_hessian
공식 코드Active Probabilistic Inference on Matrices for Pre-Conditioning in Stochastic Optimization
https://github.com/feedbackward/mrisk
공식 코드https://github.com/fergunet/SabberStone
공식 코드Optimizing Hearthstone Agents using an Evolutionary Algorithm
https://github.com/fisheggg/lvns-rave
공식 코드LVNS-RAVE: Diversified audio generation with RAVE and Latent Vector Novelty Search
https://github.com/florianrupp/geevo-game-economies
공식 코드GEEvo: Game Economy Generation and Balancing with Evolutionary Algorithms
https://github.com/flowersteam/EpidemiOptim
공식 코드EpidemiOptim: A Toolbox for the Optimization of Control Policies in Epidemiological Models
https://github.com/folivetti/eggp_paper_GECCO
공식 코드Improving Genetic Programming for Symbolic Regression with Equality Graphs
https://github.com/folivetti/srtree/blob/main/apps/eggp/README.md
공식 코드Improving Genetic Programming for Symbolic Regression with Equality Graphs
https://github.com/foolnotion/pagmo2_nds_benchmarks
공식 코드https://github.com/franrruiz/vcd_divergence
공식 코드A Contrastive Divergence for Combining Variational Inference and MCMC
https://github.com/fsschneider/deepobs
공식 코드https://github.com/gabro8a/stns-moea
공식 코드Search Trajectories Networks of Multiobjective Evolutionary Algorithms
https://github.com/galdeia/srbench
공식 코드https://github.com/gbaydin/hypergradient-descent
공식 코드https://github.com/gdkent/bsg_methods_con_unc
공식 코드Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems
https://github.com/geekyifei/randomized-PINN
공식 코드Randomized Physics-Informed Neural Networks for Bayesian Data Assimilation
https://github.com/geneura-papers/2015-ea-languages
공식 코드https://github.com/george-hall-sheff/leading_ones_recurrences_tool
공식 코드https://github.com/gibsonlab/ht_paper
공식 코드On the stability of gradient descent with second order dynamics for time-varying cost functions
https://github.com/gingsmith/cocoa
공식 코드Adding vs. Averaging in Distributed Primal-Dual Optimization
https://github.com/gingsmith/proxcocoa
공식 코드L1-Regularized Distributed Optimization: A Communication-Efficient Primal-Dual Framework
https://github.com/google-deepmind/asyncdiloco
공식 코드https://github.com/google-research/google-research
공식 코드ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.