DeepTraverse is a weight-tied residual network plus squeeze-and-excitation attention, framed as depth-first search, with claimed efficiency gains that rest on a questionable ImageNet subset comparison.
On the Performance of the Depth First Search Algorithm in Supercritical Random Graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We consider the performance of the Depth First Search (DFS) algorithm on the random graph $G\left(n,\frac{1+\epsilon}{n}\right)$, $\epsilon>0$ a small constant. Recently, Enriquez, Faraud and M\'enard [2] proved that the stack $U$ of the DFS follows a specific scaling limit, reaching the maximal height of $(1+o_{\epsilon}(1))\epsilon^2n$. Here we provide a simple analysis for the typical length of a maximum path discovered by the DFS.
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DeepTraverse: A Depth-First Search Inspired Network for Algorithmic Visual Understanding
DeepTraverse is a weight-tied residual network plus squeeze-and-excitation attention, framed as depth-first search, with claimed efficiency gains that rest on a questionable ImageNet subset comparison.