Metraipolis › archive › dc_5d7b3bc21eda

Least-time Gradient Flow — arXiv:2610.01426

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01426
License (as archived)
CC0-1.0
Archived
2026-10-06T16:01:35.387Z
SHA-256 of the archived text
2839bb8f67b88b1cdd2f08a6502136506f367573e9b905b4ed422f260caf5d06
Stable URL of this page
https://metraipolis.com/documento/dc_5d7b3bc21eda

How to cite

Least-time Gradient Flow — arXiv:2610.01426 — arXiv (en), https://arxiv.org/abs/2610.01426 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5d7b3bc21eda (Metraipolis archive dc_5d7b3bc21eda, sha256 2839bb8f67b88b1cdd2f08a6502136506f367573e9b905b4ed422f260caf5d06)
BibTeX
@misc{dc5d7b3bc21eda,
  title = {Least-time Gradient Flow — arXiv:2610.01426},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01426},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5d7b3bc21eda; sha256 2839bb8f67b88b1cdd2f08a6502136506f367573e9b905b4ed422f260caf5d06},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01426. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Prescribing the speed of gradient flow on the risk itself, by the dynamics $\dot w=-u(E(w))\nabla E(w)/\abs{\nabla E(w)}^{2}$, makes the risk $e(t)=E(w(t))$ obey $\dot e=-u(e)$ exactly, whatever the landscape~$E$; the time needed to reach zero risk from $e_0$ is $\int_0^{e_0}\dd e/u(e)$. Minimizing this time alone is ill posed, and we study the regularized problem $\inf\{\int_0^{e_0}(\tfrac\lambda2\abs{u'}^{2}+1/u)\,\dd e:\ u\in H^{1}(0,e_0),\ u\ge0,\ u(0)=0\}$, $\lambda>0$. We prove that the minimizer exists, is unique, and is a linearly scaled cycloid, and we show that the optimal rate behaves like $u^{*}(e)\sim(9/(2\lambda))^{1/3}e^{2/3}$ near zero risk: the exponent $2/3$ is the one found in \cite{betti2026holder} by a power-law ansatz, and it lies in the Hölder window $(\tfrac12,1)$ where the arrival is in finite time with vanishing weight speed. The proof follows the classical route: existence by the direct method, uniqueness by strict convexity, positivity of the minimizer away from the origin, and the explicit integration of the Euler-Lagrange equation.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-10-02 in math.OC).
Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.01426 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T15:14:58.002Z dalla pagina https://arxiv.org/catchup/math.OC/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).