Differentiable Integer Linear Programming is not Differentiable & it's not a mere technical problem

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Sornwanee, Thanawat
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917230012268544
author Sornwanee, Thanawat
author_facet Sornwanee, Thanawat
contents We show how the differentiability method employed in the paper ``Differentiable Integer Linear Programming'', Geng, et al., 2025 as shown in its theorem 5 is incorrect. Moreover, there already exists some downstream work that inherits the same error. The underlying reason comes from that, though being continuous in expectation, the surrogate loss is discontinuous in almost every realization of the randomness, for the stochastic gradient descent.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17800
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Differentiable Integer Linear Programming is not Differentiable & it's not a mere technical problem
Sornwanee, Thanawat
Optimization and Control
Machine Learning
We show how the differentiability method employed in the paper ``Differentiable Integer Linear Programming'', Geng, et al., 2025 as shown in its theorem 5 is incorrect. Moreover, there already exists some downstream work that inherits the same error. The underlying reason comes from that, though being continuous in expectation, the surrogate loss is discontinuous in almost every realization of the randomness, for the stochastic gradient descent.
title Differentiable Integer Linear Programming is not Differentiable & it's not a mere technical problem
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2601.17800