# On the Integrality Gap of Binary Integer Programs with Gaussian Data

arXiv: https://arxiv.org/abs/2012.08346 · HTML: https://mlsanity.com/paper/2012.08346/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2020.

## Built on by (most cited first, 3 of 3)

- [Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets](https://mlsanity.com/paper/2311.09858/) (2023)
- [On the Sparsity of the Strong Lottery Ticket Hypothesis](https://mlsanity.com/paper/2410.14754/) (2024)
- [A Unified Framework for Quantized and Continuous Strong Lottery Tickets](https://mlsanity.com/paper/2607.03860/) (2026)

## Abstract (arXiv)

For a binary integer program (IP) rm max ~ c^mathsfT x, Ax ≤ b, x ∈ 0,1n, where A ∈ ℝm × n and c ∈ ℝn have independent Gaussian entries and the right-hand side b ∈ ℝm satisfies that its negative coordinates have ℓ2 norm at most n/10, we prove that the gap between the value of the linear programming relaxation and the IP is upper bounded by operatornamepoly(m)(log n)2 / n with probability at least 1-2/n7-2^-operatornamepoly(m). Our results give a Gaussian analogue of the classical integrality gap result of Dyer and Frieze (Math. of O.R., 1989) in the case of random packing IPs. In constrast to the packing case, our integrality gap depends only polynomially on m instead of exponentially. Building upon recent breakthrough work of Dey, Dubey and Molinaro (SODA, 2021), we show that the integrality gap implies that branch-and-bound requires n^operatornamepoly(m) time on random Gaussian IPs with good probability, which is polynomial when the number of constraints m is fixed. We derive this result via a novel meta-theorem, which relates the size of branch-and-bound trees and the integrality gap for random logconcave IPs.