Papers with Code 아카이브
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/yeshenpy/awesome-evolutionary-reinforcement-learning
공식 코드https://github.com/yeshenpy/erl-re2
공식 코드https://github.com/yonilc/adacons
공식 코드Adaptive Consensus Gradients Aggregation for Scaled Distributed Training
https://github.com/yshenaw/GNN-Resource-Management
공식 코드https://github.com/yuxiangw/tv_online
공식 코드https://github.com/yzhao3685/stoccontextualopti
공식 코드https://github.com/zalanborsos/online-variance-reduction
공식 코드https://github.com/zalanborsos/variance-reduction-mixtures
공식 코드https://github.com/zehsilva/prior-predictive-specification
공식 코드Prior Specification for Bayesian Matrix Factorization via Prior Predictive Matching
https://github.com/zehuilu/Cooperative-Tuning-of-Multi-Agent-Optimal-Control-Systems
공식 코드https://github.com/zeinebzh/tumornetsolvers
공식 코드Efficient Deep Learning-based Forward Solvers for Brain Tumor Growth Models
https://github.com/zhao-xingyuan/must
공식 코드https://github.com/zhenhuan-yang/minimaxfairauc
공식 코드Minimax AUC Fairness: Efficient Algorithm with Provable Convergence
https://github.com/zhenxun-zhuang/SGD-Exponential-Cosine-Stepsize
공식 코드A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
https://github.com/zhenxun-zhuang/SGD-Exponential-Stepsize
공식 코드A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
https://github.com/zhqiu/ndcg-optimization
공식 코드Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence
https://github.com/zhuchen03/maxva
공식 코드MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients
https://github.com/zirui-ray-liu/wtacrs
공식 코드Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model
https://github.com/zjg540066169/TMOGA
공식 코드Transfer Learning Based Multi-Objective Genetic Algorithm for Dynamic Community Detection
https://github.com/zoesgithub/fedreg
공식 코드Acceleration of Federated Learning with Alleviated Forgetting in Local Training
https://github.com/zoom-wang112358/molleo
공식 코드Efficient Evolutionary Search Over Chemical Space with Large Language Models
https://github.com/zuhengxu/Consistent-Stochastic-Variational-Inference
공식 코드The computational asymptotics of Gaussian variational inference and the Laplace approximation
https://github.com/zweifel/zweifel
공식 코드General Subpopulation Framework and Taming the Conflict Inside Populations
https://github.com/zwx-open/evos-inr
공식 코드EVOS: Efficient Implicit Neural Training via EVOlutionary Selector
https://github.com/zyhe/distribution-dynamics-opt
공식 코드Decision-Dependent Stochastic Optimization: The Role of Distribution Dynamics
https://github.com/zyjiao4728/POG-Demo
공식 코드https://github.com/zykls/performative-prediction
공식 코드https://github.com/zzjchen/qube_code
공식 코드QUBE: Enhancing Automatic Heuristic Design via Quality-Uncertainty Balanced Evolution
https://gitlab.com/aau-adapt-t2d/t2d-adaos
공식 코드https://gitlab.com/leocus/ge_q_dts
공식 코드https://gitlab.com/nicolalandro/multi_optimizer
공식 코드https://worksheets.codalab.org/worksheets/0x610bcdb722bf48d3b537a65edf0fe72d
공식 코드https://worksheets.codalab.org/worksheets/0x621811fe446b49bb818293bae2ef88c0
공식 코드https://zenodo.org/record/14506854
공식 코드Runtime Analysis for Multi-Objective Evolutionary Algorithms in Unbounded Integer Spaces
https://github.com/1170500804/MoCo
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.