๐ฎ
๐ฎ
The Ethereal
Algorithms and Barriers in the Symmetric Binary Perceptron Model
March 29, 2022 ยท The Ethereal ยท ๐ IEEE Annual Symposium on Foundations of Computer Science
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
David Gamarnik, Eren C. Kฤฑzฤฑldaฤ, Will Perkins, Changji Xu
arXiv ID
2203.15667
Category
cs.CC: Computational Complexity
Cross-listed
cs.DS,
math-ph,
math.PR
Citations
42
Venue
IEEE Annual Symposium on Foundations of Computer Science
Last Checked
1 month ago
Abstract
The symmetric binary perceptron ($\texttt{SBP}$) exhibits a dramatic statistical-to-computational gap: the densities at which known efficient algorithms find solutions are far below the threshold for the existence of solutions. Furthermore, the $\texttt{SBP}$ exhibits a striking structural property: at all positive constraint densities almost all of its solutions are 'totally frozen' singletons separated by large Hamming distance \cite{perkins2021frozen,abbe2021proof}. This suggests that finding a solution to the $\texttt{SBP}$ may be computationally intractable. At the same time, the $\texttt{SBP}$ does admit polynomial-time search algorithms at low enough densities. A conjectural explanation for this conundrum was put forth in \cite{baldassi2020clustering}: efficient algorithms succeed in the face of freezing by finding exponentially rare clusters of large size. However, it was discovered recently that such rare large clusters exist at all subcritical densities, even at those well above the limits of known efficient algorithms \cite{abbe2021binary}. Thus the driver of the statistical-to-computational gap exhibited by this model remains a mystery. In this paper, we conduct a different landscape analysis to explain the algorithmic tractability of this problem. We show that at high enough densities the $\texttt{SBP}$ exhibits the multi Overlap Gap Property ($m-$OGP), an intricate geometrical property known to be a rigorous barrier for large classes of algorithms. Our analysis shows that the $m-$OGP threshold (a) is well below the satisfiability threshold; and (b) matches the best known algorithmic threshold up to logarithmic factors as $m\to\infty$. We then prove that the $m-$OGP rules out the class of stable algorithms for the $\texttt{SBP}$ above this threshold. We conjecture that the $m \to \infty$ limit of the $m$-OGP threshold marks the algorithmic threshold for the problem.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computational Complexity
๐ฎ
๐ฎ
The Ethereal
An Exponential Separation Between Randomized and Deterministic Complexity in the LOCAL Model
๐ฎ
๐ฎ
The Ethereal
The Parallelism Tradeoff: Limitations of Log-Precision Transformers
๐ฎ
๐ฎ
The Ethereal
The Hardness of Approximation of Euclidean k-means
๐ฎ
๐ฎ
The Ethereal
Slightly Superexponential Parameterized Problems
๐ฎ
๐ฎ
The Ethereal