A Robust Perceptron Cycling Theorem and Applications

2026-09-16

AI Summary

该研究解决了感知机循环定理的鲁棒性问题，通过引入有限集增量和非对称正定算子，为特定优化问题提供了新的迭代收敛性保证。

Abstract

The classical perceptron cycling theorem of Block and Levin \cite{BlockLevin1970} bounds correction sequences whose selected updates come from a finite set and have nonpositive inner product with the current state. We prove a robust variant for additive trajectories $z_{k+1}=z_k+u_k$, for all integers $k\geq0$, with increments in a finite set $U\subset E$, where $E$ is a finite-dimensional real inner-product space and $0\in\conv U$. Let $A\colon E\to E$ have positive-definite symmetric part, without requiring symmetry, and let $B\geq0$. If each $u_k$ is a $B$-approximate minimizer of $u\mapsto\ip{Az_k}{u}$ over $U$, then $\sup_{k\geq0}\norm{z_k}\leq C(1+\norm{z_0}+B)$, with $C=C(E,U,A)$ independent of the initial state, $B$, and all admissible update choices. Our central algorithmic consequence is an $O(k^{-1})$ last-iterate norm bound for harmonic vertex-returning Frank--Wolfe for affine strongly monotone variational inequalities on polytopes with relatively interior solutions. It extends the quadratic Frank--Wolfe/herding guarantee of Bach, Lacoste-Julien, and Obozinski \cite[Section~4.2]{BachEtAl2012} to nonsymmetric affine operators. We apply this bound to empirical best responses in strongly stable linear population games, quadratically regularized bilinear saddle problems, and traffic assignment with coercive affine asymmetric cost maps.

Problem

• perceptron
• cycling theorem
• boundedness
• asymmetric affine operator
• Frank-Wolfe method

Innovation

• Robust Perceptron Cycling Theorem
• Asymmetric Affine Operators
• Harmonic Vertex-Returning Frank--Wolfe
• Affine Strongly Monotone Variational Inequalities
• Last-Iterate Norm Bound