mlsanityData to 7 Oct 2026

Globally Convergent Type-I Anderson Acceleration for Non-Smooth Fixed-Point Iterations

arXiv 1808.03971 ↗First posted 12 Aug 2018math.OCcited by 24

Not on the map. Why?

Abstract (arXiv)

We consider the application of the type-I Anderson acceleration to solving general non-smooth fixed-point problems. By interleaving with safe-guarding steps, and employing a Powell-type regularization and a re-start checking for strong linear independence of the updates, we propose the first globally convergent variant of Anderson acceleration assuming only that the fixed-point iteration is non-expansive. We show by extensive numerical experiments that many first order algorithms can be improved, especially in their terminal convergence, with the proposed algorithm. Our proposed method of acceleration is being implemented in SCS 2.0, one of the default solvers used in the convex optimization parser-solver CVXPY 1.0.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 3; 2023: 6; 2024: 5; 2025: 4.

24 papers.

Sort:

  1. 2022Tutorial on amortized optimizationcited by 83
  2. 2023Learning to Warm-Start Fixed-Point Optimization Algorithmscited by 32
  3. 2021Joint inference and input optimization in equilibrium networkscited by 15
  4. 2023Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factorcited by 13
  5. 2021Neural Fixed-Point Acceleration for Convex Optimizationcited by 10
  6. 2023Accelerating Value Iteration with Anchoringcited by 10
  7. 2024Data-Driven Performance Guarantees for Classical and Learned Optimizerscited by 5
  8. 2022Coordinate Descent for SLOPEcited by 4
  9. 2024Advancing the Understanding of Fixed Point Iterations in Deep Neural Networks: A Detailed Analytical Studycited by 4
  10. 2021An Adaptive State Aggregation Algorithm for Markov Decision Processescited by 2
  11. 2021An Operator Splitting View of Federated Learningcited by 2
  12. 2021Weighted Low-Rank Matrix Approximation: Acceleration and Applicationscited by 2
12 more
  1. 2023Enhancing Electrical Impedance Tomography reconstruction using Learned Half-Quadratic Splitting Networks with Anderson Accelerationcited by 2
  2. 2023From Optimization to Control: Quasi Policy Iterationcited by 2
  3. 2025Rank-One Modified Value Iterationcited by 2
  4. 2021OpReg-Boost: Learning to Accelerate Online Algorithms with Operator Regressioncited by 1
  5. 2024An information-matching approach to optimal experimental design and active learningcited by 1
  6. 2025Sparse Partial Optimal Transport via Quadratic Regularizationcited by 1
  7. 2022An Efficient Nonlinear Acceleration method that Exploits Symmetry of the Hessiancited by 0
  8. 2023Improved Convergence Factor of Windowed Anderson Acceleration for Symmetric Fixed-Point Iterationscited by 0
  9. 2024Randomized Approach to Matrix Completion: Applications in Recommendation Systems and Image Inpaintingcited by 0
  10. 2024Anderson acceleration for iteratively reweighted ℓ1 algorithmcited by 0
  11. 2025Online multidimensional dictionary learningcited by 0
  12. 2025Efficient Solvers for SLOPE in R, Python, Julia, and C++cited by 0