{"url":"/method/saga","slug":"saga","name":"SAGA","full_name":"SAGA","full_name_withheld":false,"description_markdown":"SAGA is a method in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the theory behind SAG and SVRG, with better theoretical convergence rates, and has support for composite objectives where a proximal operator is used on the regulariser. Unlike SDCA, SAGA supports non-strongly convex problems directly, and is adaptive to any inherent strong convexity of the problem.","description_state":"present","introduced_year":null,"introduced_by":{"title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","paper":"/paper/saga-a-fast-incremental-gradient-method-with","first_author":"Aaron Defazio","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/saga-a-fast-incremental-gradient-method-with"},"source":{"url":"http://arxiv.org/abs/1407.0202v3","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Optimization","url":"/methods/category/optimization","pwc_aliases":[]}],"n_papers_tagged":81,"archive_num_papers":81,"papers_newest_first":[{"paper":"/paper/rethinking-verification-for-llm-code","title":"Rethinking Verification for LLM Code Generation: From Generation to Testing","date":"2025-07-09","arxiv_id":"2507.06920","n_code_links":1,"syntology":null},{"paper":null,"title":"ATMM-SAGA: Alternating Training for Multi-Module with Score-Aware Gated Attention SASV system","date":"2025-05-23","arxiv_id":"2505.18273","n_code_links":0,"syntology":null},{"paper":null,"title":"A digital perspective on the role of a stemma in material-philological transmission studies","date":"2025-05-11","arxiv_id":"2505.06938","n_code_links":0,"syntology":null},{"paper":"/paper/saga-a-security-architecture-for-governing-ai","title":"SAGA: A Security Architecture for Governing AI Agentic Systems","date":"2025-04-27","arxiv_id":"2504.21034","n_code_links":0,"syntology":{"ran":0,"of":4,"unverified":4,"pointer_only":0}},{"paper":"/paper/saga-semantic-aware-gray-color-augmentation","title":"SAGA: Semantic-Aware Gray color Augmentation for Visible-to-Thermal Domain Adaptation across Multi-View Drone and Ground-Based Vision Systems","date":"2025-04-22","arxiv_id":"2504.15728","n_code_links":2,"syntology":null},{"paper":null,"title":"Variance-Reduced Fast Operator Splitting Methods for Stochastic Generalized Equations","date":"2025-04-17","arxiv_id":"2504.13046","n_code_links":0,"syntology":null},{"paper":null,"title":"SAGA: Surface-Aligned Gaussian Avatar","date":"2024-12-01","arxiv_id":"2412.00845","n_code_links":0,"syntology":null},{"paper":null,"title":"On the SAGA algorithm with decreasing step","date":"2024-10-02","arxiv_id":"2410.03760","n_code_links":0,"syntology":null},{"paper":null,"title":"SAGA: Synthesis Augmentation with Genetic Algorithms for In-Memory Sequence Optimization","date":"2024-06-14","arxiv_id":"2406.09677","n_code_links":0,"syntology":null},{"paper":null,"title":"Variance-Reduced Fast Krasnoselkii-Mann Methods for Finite-Sum Root-Finding Problems","date":"2024-06-04","arxiv_id":"2406.02413","n_code_links":0,"syntology":null},{"paper":null,"title":"SPABA: A Single-Loop and Probabilistic Stochastic Bilevel Algorithm Achieving Optimal Sample Complexity","date":"2024-05-29","arxiv_id":"2405.18777","n_code_links":0,"syntology":null},{"paper":null,"title":"Segment Any 3D Gaussians","date":"2023-12-01","arxiv_id":"2312.00860","n_code_links":0,"syntology":null},{"paper":"/paper/promise-preconditioned-stochastic","title":"PROMISE: Preconditioned Stochastic Optimization Methods by Incorporating Scalable Curvature Estimates","date":"2023-09-05","arxiv_id":"2309.02014","n_code_links":1,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":2}},{"paper":"/paper/variance-reduction-techniques-for-stochastic","title":"Variance reduction techniques for stochastic proximal point algorithms","date":"2023-08-18","arxiv_id":"2308.09310","n_code_links":1,"syntology":null},{"paper":null,"title":"Growing and Serving Large Open-domain Knowledge Graphs","date":"2023-05-16","arxiv_id":"2305.09464","n_code_links":0,"syntology":null},{"paper":null,"title":"Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples","date":"2022-09-07","arxiv_id":"2209.03358","n_code_links":0,"syntology":null},{"paper":null,"title":"Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology","date":"2022-07-08","arxiv_id":"2207.03730","n_code_links":0,"syntology":null},{"paper":null,"title":"An Adaptive Incremental Gradient Method With Support for Non-Euclidean Norms","date":"2022-04-28","arxiv_id":"2205.02273","n_code_links":0,"syntology":null},{"paper":null,"title":"Saga: A Platform for Continuous Construction and Serving of Knowledge At Scale","date":"2022-04-15","arxiv_id":"2204.07309","n_code_links":0,"syntology":null},{"paper":"/paper/a-framework-for-bilevel-optimization-that","title":"A framework for bilevel optimization that enables stochastic and global variance reduction algorithms","date":"2022-01-31","arxiv_id":"2201.13409","n_code_links":1,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":2}},{"paper":"/paper/saga-stochastic-whole-body-grasping-with","title":"SAGA: Stochastic Whole-Body Grasping with Contact","date":"2021-12-19","arxiv_id":"2112.10103","n_code_links":1,"syntology":{"ran":2,"of":4,"unverified":2,"pointer_only":0}},{"paper":null,"title":"Siamese Attribute-missing Graph Auto-encoder","date":"2021-12-09","arxiv_id":"2112.04842","n_code_links":0,"syntology":null},{"paper":"/paper/surrogate-assisted-genetic-algorithm-for","title":"Surrogate-Assisted Genetic Algorithm for Wrapper Feature Selection","date":"2021-11-17","arxiv_id":"2111.09074","n_code_links":1,"syntology":null},{"paper":null,"title":"ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computations","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computation","date":"2021-03-02","arxiv_id":"2103.01447","n_code_links":0,"syntology":null},{"paper":null,"title":"A New Framework for Variance-Reduced Hamiltonian Monte Carlo","date":"2021-02-09","arxiv_id":"2102.04613","n_code_links":0,"syntology":null},{"paper":null,"title":"Segmentation and genome annotation algorithms","date":"2021-01-03","arxiv_id":"2101.00688","n_code_links":0,"syntology":null},{"paper":null,"title":"Tight Lower Complexity Bounds for Strongly Convex Finite-Sum Optimization","date":"2020-10-17","arxiv_id":"2010.08766","n_code_links":0,"syntology":null},{"paper":null,"title":"Asynchronous Distributed Optimization with Stochastic Delays","date":"2020-09-22","arxiv_id":"2009.10717","n_code_links":0,"syntology":null},{"paper":null,"title":"Variance Reduced EXTRA and DIGing and Their Optimal Acceleration for Strongly Convex Decentralized Optimization","date":"2020-09-09","arxiv_id":"2009.04373","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/stochastic-optimization","name":"Stochastic Optimization","papers":11},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":7},{"task":"/task/distributed-optimization","name":"Distributed Optimization","papers":3},{"task":"/task/federated-learning","name":"Federated Learning","papers":3},{"task":"/task/bilevel-optimization","name":"Bilevel Optimization","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/3dgs","name":"3DGS","papers":1},{"task":"/task/adversarial-attack","name":"Adversarial Attack","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":1},{"task":"/task/clustering","name":"Clustering","papers":1},{"task":"/task/code-generation","name":"Code Generation","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/distributed-computing","name":"Distributed Computing","papers":1},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":1},{"task":"/task/dynamic-reconstruction","name":"Dynamic Reconstruction","papers":1},{"task":"/task/entity-linking","name":"Entity Linking","papers":1},{"task":"/task/fact-verification","name":"Fact Verification","papers":1},{"task":"/task/graph-representation-learning","name":"Graph Representation Learning","papers":1}],"tasks_shown":20,"n_tasks":39,"usage_by_year":[{"year":"2014","papers":1},{"year":"2015","papers":5},{"year":"2016","papers":4},{"year":"2017","papers":13},{"year":"2018","papers":12},{"year":"2019","papers":12},{"year":"2020","papers":7},{"year":"2021","papers":7},{"year":"2022","papers":5},{"year":"2023","papers":4},{"year":"2024","papers":5},{"year":"2025","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/saga"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}