Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$

• URL: http://arxiv.org/abs/2607.21579v1
• Date: Thu, 23 Jul 2026 17:56:05 GMT
• Title: Barzilai-Borwein Fails Superlinear Convergence on an Open Set of Quadratics for Every Dimension $n\geq 4$
• Abstract summary: We show that Barzilai--Borwein (BB) method converges but cannot converge root-superlinearly.<n>The construction is nontrivial, based on a computer-assisted proof of a nonresonant.
• Score: 12.018537165567055
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Barzilai--Borwein (BB) method has shown strong practical performance in continuous optimization, yet its convergence dynamics remains poorly understood. In particular, a central unresolved question is whether BB converges superlinearly for almost every strictly convex quadratic problem and initialization. We provide a negative answer to this question. Specifically, for every finite dimension $n\geq4$, we construct a nonempty open, hence positive-Lebesgue-measure, family of strictly convex quadratic problems and initial points for which the long Barzilai--Borwein method (BB1) converges but cannot converge root-superlinearly. More precisely, with the explicit constants $ρ_{\min}=10^{-6},ρ_{\max}=0.61$, every spectral component of the gradient is bounded above and below by the corresponding geometric sequence. Consequently, the gradient norm and the energy norm of the error satisfy two-sided geometric estimates with the same rates, while the objective gap satisfies the corresponding estimates with squared rates. In particular, all three quantities are bounded below by geometric sequences, ruling out superlinear convergence. The construction is highly nontrivial, based on a computer-assisted proof of a nonresonant, attracting seven-cycle of the projectivized BB dynamics in dimension four.

Related papers

• Nonconvex Composite Functional Constraints via First-Order Augmented Lagrangian Methods under Local Regularity [10.643433352418915]
  We show uniformly augmented condition bounds of primal non-balancing non-concave minimax reformulation.<n>With dual regularization, a global local argument together with a bias.<n>$KKT.
  arXiv  Detail & Related papers  (2026-07-09T21:28:29Z)
• Dimension Reduction for Curves: Simplified and Generalized [56.23281156053955]
  We revisit random projections for reducing the dimension of high-dimensional polygonal curves.<n>We give a simplified proof of the known $O(varepsilon-2log(nm))$ bound on the target dimension of a random projection.<n>Our proof is based on the concept of sparse oblivious subspace embeddings.
  arXiv  Detail & Related papers  (2026-07-03T08:48:35Z)
• Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds [61.14405512940818]
  We show that Score-based generative models are trained in high-dimensional ambient spaces.<n>We use a ReLU implementation of nearest-projection coordinates via finite intrinsic anchors and Gauss Newton.
  arXiv  Detail & Related papers  (2026-05-15T10:20:05Z)
• Trajectory-Restricted Optimization Conditions and Geometry-Aware Linear Convergence [0.764671395172401]
  We develop a trajectory-restricted framework for linear convergence based on localized geometric regularity.<n>We show that classical convergence guarantees extend under these localized conditions.<n>Our work provides a geometric quantification for fast local convergence after active-set or manifold identification.
  arXiv  Detail & Related papers  (2026-04-18T17:02:06Z)
• An Information-Minimal Geometry for Qubit-Efficient Optimization [0.0]
  We recast qubit-efficient optimization as a geometry problem.<n>Local-consistency problem coincides exactly with the Sherali-Adams level-2 polytope $mathrmSA(2)$.
  arXiv  Detail & Related papers  (2025-11-11T15:38:57Z)
• Entropic Mirror Descent for Linear Systems: Polyak's Stepsize and Implicit Bias [55.72269695392027]
  This paper focuses on applying entropic mirror descent to solve linear systems.<n>The main challenge for the convergence analysis stems from the unboundedness of the domain.<n>To overcome this without imposing restrictive assumptions, we introduce a variant of Polyak-type stepsizes.
  arXiv  Detail & Related papers  (2025-05-05T12:33:18Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Convergence of Adam Under Relaxed Assumptions [72.24779199744954]
  We show that Adam converges to $epsilon$-stationary points with $O(epsilon-4)$ gradient complexity under far more realistic conditions. We also propose a variance-reduced version of Adam with an accelerated gradient complexity of $O(epsilon-3)$.
  arXiv  Detail & Related papers  (2023-04-27T06:27:37Z)
• SPIRAL: A superlinearly convergent incremental proximal algorithm for nonconvex finite sum minimization [11.15617238382324]
  SPIRAL is a convergent pRoximal ALgogomrithor for finite sum problems. It has remarkable convergence under mild assumptions. It is competitive to the state of the art.
  arXiv  Detail & Related papers  (2022-07-17T14:58:06Z)
• Randomized Coordinate Subgradient Method for Nonsmooth Composite Optimization [11.017632675093628]
  Coordinate-type subgradient methods for addressing nonsmooth problems are relatively underexplored due to the set of properties of the Lipschitz-type assumption.
  arXiv  Detail & Related papers  (2022-06-30T02:17:11Z)
• Last iterate convergence of SGD for Least-Squares in the Interpolation regime [19.05750582096579]
  We study the noiseless model in the fundamental least-squares setup. We assume that an optimum predictor fits perfectly inputs and outputs $langle theta_*, phi(X) rangle = Y$, where $phi(X)$ stands for a possibly infinite dimensional non-linear feature map.
  arXiv  Detail & Related papers  (2021-02-05T14:02:20Z)
• A Simple Convergence Proof of Adam and Adagrad [74.24716715922759]
  We show a proof of convergence between the Adam Adagrad and $O(d(N)/st)$ algorithms. Adam converges with the same convergence $O(d(N)/st)$ when used with the default parameters.
  arXiv  Detail & Related papers  (2020-03-05T01:56:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.