OrderNet: Ordering by Example

05/27/2019
by   Robert Porter, et al.
0

In this paper we introduce a new neural architecture for sorting unordered sequences where the correct sequence order is not easily defined but must rather be inferred from training data. We refer to this architecture as OrderNet and describe how it was constructed to be naturally permutation equivariant while still allowing for rich interactions of elements of the input set. We evaluate the capabilities of our architecture by training it to approximate solutions for the Traveling Salesman Problem and find that it outperforms previously studied supervised techniques in its ability to generalize to longer sequences than it was trained with. We further demonstrate the capability by reconstructing the order of sentences with scrambled word order.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/09/2015

Pointer Networks

We introduce a new neural architecture to learn the conditional probabil...
research
08/22/2022

Analysis of Approximate sorting in I/O model

We consider the problem of approximate sorting in I/O model. The goal of...
research
06/08/2022

Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction

The task of learning to map an input set onto a permuted sequence of its...
research
06/28/2023

Permutation Polynomial Interleaved Zadoff-Chu Sequences

Constant amplitude zero autocorrelation (CAZAC) sequences have modulus o...
research
10/25/2019

A Curious Link Between Prime Numbers, the Maundy Cake Problem and Parallel Sorting

We present new theoretical algorithms that sums the n-ary comparators ou...
research
02/14/2012

Reasoning about RoboCup Soccer Narratives

This paper presents an approach for learning to translate simple narrati...

Please sign up or login with your details

Forgot password? Click here to reset