REVIEW 1 cited by
The Gronwall inequality
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
The Gronwall inequality
read the original abstract
We prove the following version generalization of the Gronwall inequality: Let $\mathbf X$ be a Banach space and $U\subset \mathbf X$ an open convex set in $\mathbf X$. Let $f,g\colon [a,b]\times U\to \mathbf X$ be continuous functions and let $y,z\colon [a,b]\to U$ satisfy the initial value problems \begin{align*} y'(t)&=f(t,y(t)),\quad y(a)=y_0,\\ z'(t)&=g(t,z(t)),\quad z(a)=z_0. \end{align*} Also assume there is a constant $C\ge 0$ so that $$ \|g(t,x_2)-g(t,x_1)\|\le C\|x_2-x_1\| $$ and a continuous function $\phi\colon [a,b]\to [0,\infty)$ so that $$ \|f(t,y(t))-g(t,y(t))\|\le \phi(t). $$ Then for $t\in [a,b]$ $$ \|y(t)-z(t)\| \le e^{C|t-a|}\|y_0-z_0\|+e^{C|t-a|}\int_a^te^{-C|s-a|}\phi(s)\,ds. $$
Forward citations
Cited by 1 Pith paper
-
Generalization Bounds of Spiking Neural Networks via Rademacher Complexity
Spiking neural networks have Rademacher complexity bounds that scale exponentially with depth and spike sequence duration, superlinearly and subquadratically with width, polynomially with parameter norm, and inversely...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.