paper-with-me

Papers

Restricted Dynamic Geometric Complexity: Certificates for Structured Preconditioning

2026-07-08 · Zavier Li arxiv

Optimization geometrodynamics views optimizer state as evolving geometry. Its full positive-definite quadratic benchmark gives the least affine-invariant deformation needed to reduce condition number when arbitrary metrics are allowed. This paper records that benchmark in the present notation and develops restricted dynamic geometric complexity: an intrinsic certificate distance for reaching a target condition-number class when the metric is restricted to a specified family. The main proved results are monotonicity and submanifold-distance principles, diagonal and block reachability as linear matrix inequality feasibility problems, an exact two-dimensional diagonal complexity formula, and affine-invariant Kronecker projection theorems with normal equations, computable mismatch certificates, Armijo solver convergence, auxiliary self-conditioned K-target bounds, and Hessian-relative candidate certificates through an exact Kronecker Loewner-sandwich reachability condition, including a Kronecker expression threshold and a fixed-basis exact subproblem. Low-rank spectral models, curvature-proxy inflation, stochastic restricted complexity, discrete geometric length, and expression--estimation--flow--discretization accounting are presented as diagnostic interfaces rather than full optimizer characterizations. The resulting language turns structural preconditioner questions into geometric distance, reachability, and certificate problems. The repository includes deterministic toy and synthetic workflows that check diagonal expression gaps, block primal/dual certificates, Kronecker spectral width, and Hessian-relative Kronecker candidate certificates on small quadratic instances, together with low-rank spectral monotonicity.

📄 PDF Abstract BibTeX arXiv:2607.07204

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Structured Estimation with Atomic Norms: General Bounds and Applications

2015-12-01 · NeurIPS 2015 12 · Sheng Chen, Arindam Banerjee

For structured estimation problems with atomic norms, recent advances in the literature express sample complexity and estimation error bounds in terms of certain geometric measures, in particular Gaussian width of the un…

The Approximation Rank of Softmax Attention: Sharp Geometric Laws and Robust Interaction Dimension

2026-08-28 · Yuhe Sui, Jianing Zhang arxiv

Which geometry controls the rank complexity of normalized softmax attention? We study maximum-row-$\ell_1$ approximation rank, exactly the least unrestricted rank preserving every bounded vector-valued output. Two sharp …

Automated and Formal Synthesis of Neural Barrier Certificates for Dynamical Models

2020-07-07 · Andrea Peruffo, Daniele Ahmed, Alessandro Abate

We introduce an automated, formal, counterexample-based approach to synthesise Barrier Certificates (BC) for the safety verification of continuous and hybrid dynamical models. The approach is underpinned by an inductive …

Adversarially Robust Stability Certificates can be Sample-Efficient

2021-12-20 · Thomas T. C. K. Zhang, Stephen Tu, Nicholas M. Boffi, Jean-Jacques E. Slotine 외

Motivated by bridging the simulation to reality gap in the context of safety-critical systems, we consider learning adversarially robust stability certificates for unknown nonlinear dynamical systems. In line with approa…

Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning

2025-02-23 · Avinandan Bose, Laurent Lessard, Maryam Fazel, Krishnamurthy Dj Dvijotham

The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data poisoning, necessitating the study of robustness of learning algorithms against such …

Binary ClassificationData Poisoning