paper
arXiv cs.LG
October 28th, 2026 at 4:00 AM

When Are Nesterov Trajectories Eventually Locally Minimizing?

arXiv:2610.33341v1 Announce Type: cross Abstract: We revisit the variational characterization of Nesterov's celebrated method and study when Nesterov trajectories are eventually locally minimizing in a variational sense, a notion that we define precisely. We show that this question is equivalent to the nonnegativity of an associated Schr\"odinger operator acting on variations of the trajectory. For power objectives of the form \[ f(x)=\frac{1}{p}\|x\|^p \] (where $\| \cdot\|$ denotes the Euclidean norm), we give a complete characterization: Among all exponents $p\ge 2$, the Nesterov trajectory with non-zero initial position is eventually locally minimizing if and only if $p=4$. We further interpret this exceptional exponent through the stability theory of semilinear elliptic equations.

#research

Get stories like this every Monday

The week's most important AI news in one email. Free, unsubscribe anytime.

Score: 2.82

Engagement proxy: 0

Canonical link: https://arxiv.org/abs/2610.33341