Tight lipschitz hardness for optimizing mean field spin glasses
We study the problem of algorithmically optimizing the Hamiltonian of a spherical or Ising
mean field spin glass. The maximum asymptotic value OPT of this random function is …
mean field spin glass. The maximum asymptotic value OPT of this random function is …
[HTML][HTML] Reducibility and computational lower bounds for problems with planted sparse structure
M Brennan, G Bresler… - Conference On Learning …, 2018 - proceedings.mlr.press
Recently, research in unsupervised learning has gravitated towards exploring statistical-
computational gaps induced by sparsity. A line of work initiated in Berthet and Rigollet …
computational gaps induced by sparsity. A line of work initiated in Berthet and Rigollet …
Limits of local algorithms over sparse random graphs
D Gamarnik, M Sudan - Proceedings of the 5th conference on …, 2014 - dl.acm.org
Local algorithms on graphs are algorithms that run in parallel on the nodes of a graph to
compute some global structural feature of the graph. Such algorithms use only local …
compute some global structural feature of the graph. Such algorithms use only local …
The algorithmic phase transition of random k-sat for low degree polynomials
Let Φ be a uniformly random k-SAT formula with n variables and m clauses. We study the
algorithmic task of finding a satisfying assignment of Φ. It is known that satisfying …
algorithmic task of finding a satisfying assignment of Φ. It is known that satisfying …
Information-theoretic thresholds for community detection in sparse networks
We give upper and lower bounds on the information-theoretic threshold for community
detection in the stochastic block model. Specifically, consider a symmetric stochastic block …
detection in the stochastic block model. Specifically, consider a symmetric stochastic block …
The overlap gap property and approximate message passing algorithms for -spin models
D Gamarnik, A Jagannath - 2021 - projecteuclid.org
We consider the algorithmic problem of finding a near ground state (near optimal solution) of
a p-spin model. We show that for a class of algorithms broadly defined as Approximate …
a p-spin model. We show that for a class of algorithms broadly defined as Approximate …
Optimal low-degree hardness of maximum independent set
AS Wein - Mathematical Statistics and Learning, 2022 - content.ems.press
We study the algorithmic task of finding a large independent set in a sparse Erdos–Rényi
random graph with n vertices and average degree d. The maximum independent set is …
random graph with n vertices and average degree d. The maximum independent set is …
Modern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent set
MC Angelini, F Ricci-Tersenghi - Nature Machine Intelligence, 2023 - nature.com
The recent work by Schuetz et al. 1 'Combinatorial optimization with physics-inspired graph
neural networks' introduces a physics-inspired unsupervised graph neural network (GNN) to …
neural networks' introduces a physics-inspired unsupervised graph neural network (GNN) to …
Algorithms and barriers in the symmetric binary perceptron model
The binary (or Ising) perceptron is a toy model of a single-layer neural network and can be
viewed as a random constraint satisfaction problem with a high degree of connectivity. The …
viewed as a random constraint satisfaction problem with a high degree of connectivity. The …
Sum-of-squares lower bounds for sparse independent set
The Sum-of-Squares (SoS) hierarchy of semidefinite programs is a powerful algorithmic
paradigm which captures state-of-the-art algorithmic guarantees for a wide array of …
paradigm which captures state-of-the-art algorithmic guarantees for a wide array of …