SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.07174 · ICLR · 2024

Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions

Jungtaek Kim, Minsu Cho, Jeongbeen Yoon

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

FunctionStatusWhere it lives
NormalCDF Ran jungtaekkim/error-free-differentiable-swap-functions/error_free_dsf/diffsort.py
code served (permissive licence) · get_code("fb319844337f8bbe")
bitonic_network Ran jungtaekkim/error-free-differentiable-swap-functions/error_free_dsf/diffsort.py
code served (permissive licence) · get_code("1d0595393af5a124")
get_sorting_network Ran jungtaekkim/error-free-differentiable-swap-functions/error_free_dsf/diffsort.py
code served (permissive licence) · get_code("d080a1496f717ea5")
odd_even_network Ran jungtaekkim/error-free-differentiable-swap-functions/error_free_dsf/diffsort.py
code served (permissive licence) · get_code("567cb1ff7a369175")
s_best Ran jungtaekkim/error-free-differentiable-swap-functions/error_free_dsf/diffsort.py
code served (permissive licence) · get_code("5e1f120cec901868")
DiffSortNet Not yet run jungtaekkim/error-free-differentiable-swap-functions/error_free_dsf/diffsort.py
code served (permissive licence) · get_code("8c04c53e64c34ed7")
execute_sort Not yet run jungtaekkim/error-free-differentiable-swap-functions/error_free_dsf/diffsort.py
code served (permissive licence) · get_code("370f0b2b61a7170b")
sort Not yet run jungtaekkim/error-free-differentiable-swap-functions/error_free_dsf/diffsort.py
code served (permissive licence) · get_code("ea0e71f13ae5af2c")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Sorting is a fundamental operation of all computer systems, having been a longstanding significant research topic. Beyond the problem formulation of traditional sorting algorithms, we consider sorting problems for more abstract yet expressive inputs, e.g., multi-digit images and image fragments, through a neural sorting network. To learn a mapping from a high-dimensional input to an ordinal variable, the differentiability of sorting networks needs to be guaranteed. In this paper we define a softening error by a differentiable swap function, and develop an error-free swap function that holds a non-decreasing condition and differentiability. Furthermore, a permutation-equivariant Transformer network with multi-head attention is adopted to capture dependency between given inputs and also leverage its model capacity with self-attention. Experiments on diverse sorting benchmarks show that our methods perform better than or comparable to baseline methods.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.07174")
get_code_for_paper("2310.07174")
have("2310.07174")

Connect an agent — have() is free.