Lune

ICLR2025Top-tier venue

ADMM for Structured Fractional Minimization

Ganzhao Yuan

Abstract

This paper considers a class of structured fractional minimization problems. The numerator consists of a differentiable function, a simple nonconvex nonsmooth function, a concave nonsmooth function, and a convex nonsmooth function composed with a linear operator. The denominator is a continuous function that is either weakly convex or has a weakly convex square root. These problems are prevalent in various important applications in machine learning and data science. Existing methods, primarily based on subgradient methods and smoothing proximal gradient methods, often suffer from slow convergence and numerical stability issues. In this paper, we introduce FADMM, the first Alternating Direction Method of Multipliers tailored for this class of problems. FADMM decouples the original problem into linearized proximal subproblems, featuring two variants: one using Dinkelbach's parametric method (FADMM-D) and the other using the quadratic transform method (FADMM-Q). By introducing a novel Lyapunov function, we establish that FADMM converges to ǫ-approximate critical points of the problem within an oracle complexity of O(1/ǫ 3 ). Extensive experiments on synthetic and real-world datasets, including sparse Fisher discriminant analysis, robust Sharpe ratio minimization, and robust sparse recovery, demonstrate the effectiveness of our approach. 1

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • ADMM for Nonconvex Optimization under Minimal Continuity Assumption cites A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max Problems
  • ADMM for Nonconvex Optimization under Minimal Continuity Assumption cites Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence
  • Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence cites Coordinate Descent Methods for Fractional Minimization
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. ADMM for Nonconvex Optimization under Minimal Continuity AssumptionGanzhao YuanICLR 2025

Builds on4

  1. A Single-Loop Smoothed Gradient Descent-Ascent Algorithm for Nonconvex-Concave Min-Max ProblemsJiawei Zhang, Peijun Xiao, Ruoyu Sun, Zhi-Quan LuoNeurIPS 2020 · 130 citations
  2. Coordinate Descent Methods for Fractional MinimizationGanzhao YuanICML 2023 · 7 citations
  3. Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global ConvergenceGanzhao YuanICML 2024 · 6 citations
  4. ADMM for Nonconvex Optimization under Minimal Continuity AssumptionGanzhao YuanICLR 2025

Related papers

  1. Last-iterate Convergence of ADMM on Multi-affine Quadratic Equality Constrained ProblemYutong Chao, Michal Ciebielski, Jalal Etesami, Majid KhadivICML 2026
  2. NysADMM: faster composite convex optimization via low-rank approximationShipu Zhao, Zachary Frangella, Madeleine UdellICML 2022 · 10 citations
  3. Hybrid Variance-Reduced SGD Algorithms For Minimax Problems with Nonconvex-Linear FunctionQuoc Tran-Dinh, Deyi Liu, Lam M. NguyenNeurIPS 2020 · 28 citations
  4. A proximal ADMM for multiblock problems with block anti-upper triangular constraintsZhanwang Deng, Yuqiu Su, Wen HuangICML 2026
  5. Adaptive First-Order Methods Revisited: Convex Minimization without Lipschitz RequirementsKimon Antonakopoulos, Panayotis MertikopoulosNeurIPS 2021 · 13 citations
Dusk over the sea between two cliffs drawn in fine vertical lines