English
Related papers

Related papers: Reinforcement learning for graph theory, II. Small…

200 papers

Graphs are a natural representation for systems based on relations between connected entities. Combinatorial optimization problems, which arise when considering an objective function related to a process of interest on discrete structures,…

Machine Learning · Computer Science 2024-08-21 Victor-Alexandru Darvariu , Stephen Hailes , Mirco Musolesi

We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to…

Machine Learning · Statistics 2019-09-25 Ian Osband , Benjamin Van Roy , Daniel Russo , Zheng Wen

A major line of research is discovering Ramsey-type theorems, which are results of the following form: given a graph parameter $\rho$, every graph $G$ with sufficiently large $\rho(G)$ contains a `well-structured' induced subgraph $H$ with…

Combinatorics · Mathematics 2018-08-15 Ilkyoo Choi , Michitaka Furuya , Ringi Kim , Boram Park

The $(m,n)$-online Ramsey game is a combinatorial game between two players, Builder and Painter. Starting from an infinite set of isolated vertices, Builder draws an edge on each turn and Painter immediately paints it red or blue. Builder's…

Combinatorics · Mathematics 2018-11-06 David Conlon , Jacob Fox , Andrey Grinshpun , Xiaoyu He

Expander graphs, due to their mixing properties, are useful in many algorithms and combinatorial constructions. One can produce an expander graph with high probability by taking a random graph (e.g., the union of $d$ random bijections for a…

Combinatorics · Mathematics 2024-05-30 Geoffroy Caillat-Grenier

Using cyclic graphs I give new lower bounds for two color and multicolor Ramsey numbers: R(4,16)>163, R(5,11)>170, R(5,12)>190, R(5,13)>212, R(5,14)>238, R(3,3,9)>117, R(3,3,10)>141 and R(3,3,11)>157. Improving the previous best known…

Combinatorics · Mathematics 2010-05-07 Robert Gerbicz

We propose a model of network formation based on reinforcement learning, which can be seen as a generalization as the one proposed by Skyrms for signaling games. On a discrete graph, whose vertices represent individuals, at any time step…

Probability · Mathematics 2016-02-08 Daniel Kious , Pierre Tarrès

Large sparse linear systems of equations are ubiquitous in science and engineering, such as those arising from discretizations of partial differential equations. Algebraic multigrid (AMG) methods are one of the most common methods of…

Machine Learning · Computer Science 2022-01-05 Ali Taghibakhshi , Scott MacLachlan , Luke Olson , Matthew West

In this paper we explore methods to exploit symmetries for ensuring sample efficiency in reinforcement learning (RL), this problem deserves ever increasing attention with the recent advances in the use of deep networks for complex RL tasks…

Machine Learning · Statistics 2017-06-12 Anuj Mahajan , Theja Tulabandhula

We introduce a statistical framework for estimating Ramsey numbers by embedding two-color Ramsey instances into a $Z_2 \times Z_2$-graded Majorana algebra. This approach replaces brute-force enumeration with two randomized spectral…

Quantum Physics · Physics 2025-09-12 Fabrizio Tamburini

We consider the problem of providing nonparametric confidence guarantees for undirected graphs under weak assumptions. In particular, we do not assume sparsity, incoherence or Normality. We allow the dimension $D$ to increase with the…

Statistics Theory · Mathematics 2013-09-27 Larry Wasserman , Mladen Kolar , Alessandro Rinaldo

We reveal a connection between the incompressibility method and the Lovasz local lemma in the context of Ramsey theory. We obtain bounds by repeatedly encoding objects of interest and thereby compressing strings. The method is demonstrated…

Combinatorics · Mathematics 2008-04-07 Pascal Schweitzer

We construct an edge-colored digraph analogous to Mathon's construction for undirected graphs. We show that this graph is connected to the $k$-th power Paley digraphs and we use this connection to produce improved lower bounds for…

Combinatorics · Mathematics 2024-08-13 Dermot McCarthy , Chris Monico

In this paper we introduce a new simple but powerful general technique for the study of edge- and vertex-reinforced processes with super-linear reinforcement, based on the use of order statistics for the number of edge, respectively of…

Probability · Mathematics 2016-06-03 Codina Cotar , Debleena Thacker

A numbering $f$ of a graph $G$ of order $n$ is a labeling that assigns distinct elements of the set $\{1,2, \ldots, n \}$ to the vertices of $G$. The strength $\mathrm{str}\left(G\right) $ of $G$ is defined by $\mathrm{str}\left( G\right)…

Combinatorics · Mathematics 2023-11-28 Rikio Ichishima , Francesc A. Muntaner-Batle , Yukio Takahashi

This paper presents a new approach to the solution of Probabilistic Risk Assessment (PRA) models using the combination of Reinforcement Learning (RL) and Graph Neural Networks (GNNs). The paper introduces and demonstrates the concept using…

Systems and Control · Electrical Eng. & Systems 2024-02-29 Joachim Grimstad , Andrey Morozov

For two graphs $G^<$ and $H^<$ with linearly ordered vertex sets, the ordered Ramsey number $r_<(G^<,H^<)$ is the minimum $N$ such that every red-blue coloring of the edges of the ordered complete graph on $N$ vertices contains a red copy…

Combinatorics · Mathematics 2022-10-12 Martin Balko , Marian Poljak

Building on recent work of Mattheus and Verstra\"ete, we establish a general connection between Ramsey numbers of the form $r(F,t)$ for $F$ a fixed graph and a variant of the Zarankiewicz problem asking for the maximum number of 1s in an…

Combinatorics · Mathematics 2024-04-25 David Conlon , Sam Mattheus , Dhruv Mubayi , Jacques Verstraëte

Deep learning has been shown to be successful in a number of domains, ranging from acoustics, images, to natural language processing. However, applying deep learning to the ubiquitous graph data is non-trivial because of the unique…

Machine Learning · Computer Science 2020-03-16 Ziwei Zhang , Peng Cui , Wenwu Zhu

Various recent proposals increase the distinguishing power of Graph Neural Networks GNNs by propagating features between $k$-tuples of vertices. The distinguishing power of these "higher-order'' GNNs is known to be bounded by the…

Machine Learning · Computer Science 2021-06-15 Pablo Barceló , Floris Geerts , Juan Reutter , Maksimilian Ryschkov