betaFeedback

WorksMathematics

Implicit Neural Representations for Variational Problems on Graphons

Abstract

We propose a neural exploratory framework for variational problems over graphons, i.e., symmetric measurable functions [0,1]2→[0,1][0,1]^2 \to [0,1], that arise as limits of dense graph sequences. Such problems are central to two parts of the mathematical literature: extremal graph theory, which studies graph parameter optimisation under given restrictions, often for those graphs with a large number of vertices, and the large deviation theory of dense random graphs, which characterises the structure of rare events through constrained graphon optimisation. We represent graphons by implicit neural networks and optimise graphon objectives by gradient descent. Our design combines three ingredients: a multi-scale sinusoidal residual architecture biased toward sharp, step-like graphons; an embedded solver that enforces a single empirical density constraint and is differentiated by implicit differentiation; and symmetry-aware Monte Carlo estimators. On generalised Turán problems that previously required substantial human effort, our framework rediscovers known optimal graphons without human intervention. Applied to open instances, it produces candidate optima, including a previously unreported family of extremal structures. Applied to the variational problems from the large deviation theory of Erdős–Rényi random graphs, the framework produces new candidate optimal graphons across both upper- and lower-tail regimes for multiple pattern graphs; for the case of the triangle graph and the upper-tail regime, these candidates improve upon the best-known reference construction of Lubetzky and Zhao. The structures found by our framework have also led to new theorems on the optimal graphons for both families of problems.

Introduction

Machine learning is opening new directions in mathematical discovery. Recent work spans automatic provers and autoformalisation for Olympiad-style or research-level problems [38, 46, 21, 49, 19, 18, 1], neural search for combinatorial constructions [48, 7, 43, 33], and pattern-driven progress on long-standing conjectures in pure mathematics [11, 17]. In this paper, we extend this line of research to a class of continuous optimisation problems over graphons, with two motivating problem families drawn from extremal graph theory and the large deviation theory of dense random graphs.

A central object in extremal graph theory is the homomorphism density t(H,G)t(H,G) between finite undirected simple graphs HH and GG: the probability that a uniformly random map from V(H)V(H) to V(G)V(G) is a graph homomorphism. As a basic example, the constrained optimisation problem

max⁡G t(K2,G)subject tot(K3,G)=0 ∧ ∣V(G)∣=n(1)\max_G\ t(K_2,G)\quad\text{subject to}\quad t(K_3,G)=0\ \wedge\ |V(G)|=n \tag*{(1)}

asks for an nn-vertex triangle-free graph that maximises the edge density. Here KmK_m denotes the complete graph on mm vertices, so K2K_2 and K3K_3 represent an edge and a triangle, respectively. Although the answer is given by the classical theorem of Mantel [28], a large family of similar problems involving homomorphism densities remains open [44, 6].

A standard approach to such problems is to study their asymptotic counterparts, taking n→∞n \to\infty and analysing the limit of the optimum. These asymptotic problems can often be reformulated as continuous optimisation over graphons, i.e., symmetric measurable functions [0,1]2→[0,1][0,1]^2 \to[0,1], that arise as limit objects of dense graph sequences [26, 24]. Another source of graphon optimisation problems comes from the large deviation theory of dense random graphs [8], where the limiting structure of an Erdős–Rényi graph conditioned on an unusually large or small homomorphism density is itself characterised by a constrained optimisation over graphons. In both settings, the objective and constraints are integrals against the graphon WW (homomorphism densities or pointwise relative entropy), and known or conjectured optima are step-like.

We attack these graphon-optimisation problems directly with deep learning, representing a graphon WW as a neural network in the spirit of implicit neural representations [35, 30, 10] and minimising the objective by gradient descent on the network parameters. Three recurring challenges shape our design. First, known and conjectured optima are typically step-like, and standard architectures struggle with such targets because of their bias toward smooth functions. We address this with a multi-scale sinusoidal residual architecture that injects sinusoidal encodings of growing frequency into successive layers, biasing the model toward sharp, step-like solutions. Second, the problems often carry a single scalar density constraint (a fixed homomorphism density) that is poorly handled by penalty terms; we embed a numerical solver for an empirical version of the constraint into the forward pass and backpropagate through it via implicit differentiation, as in deep equilibrium models [3]. Third, both the objective and the constraints are graphon integrals that must be estimated from samples, including the high-dimensional homomorphism-density integrals; we use symmetry-aware Monte Carlo estimators.

We demonstrate our framework on two families of graphon optimisation problems: (P1) generalised Turán problems from extremal graph theory, minimising a homomorphism density under a fixed edge-density constraint; and (P2) the variational problems from the large deviation theory of dense random graphs [8], minimising a relative-entropy functional under a fixed homomorphism-density constraint. On (P1), our framework rediscovers nontrivial known optima that previously required substantial human effort [16, 5, 25, 15, 40], produces candidate minimisers for open instances such as minimisation of C7C_7-homomorphism density, and through a systematic sweep over small graphs, uncovers, for a six-vertex graph, a previously unreported family of extremal structures that do not match the complete kk-partite pattern of classical examples. Applied to (P2), the framework produces new candidate optimal graphons, in the cases where the optimal structure is not fully understood, for four pattern graphs in the upper-tail regime and K3K_3 in the lower-tail regime. For K3K_3, these candidates consistently improve upon the reference construction of Lubetzky and Zhao [2015] in the upper-tail regime. We view the framework as a flexible exploratory tool that complements rigorous lower-bound techniques such as flag algebras [39, 14]: it produces candidate upper bounds, concrete candidate minimisers, and structural conjectures that can be inspected, refined, or subsequently certified. The structures found by our method have also led to new theorems (§D). For problems of (P1), the balanced complete kk-partite graphon minimises the density of every odd cycle at p=1−1/kp = 1 - 1/k for every k≥3k \ge3, and that of every connected chordal graph whose maximal cliques have a common size r≥3r \ge3 at p=1−1/kp = 1 - 1/k for every k≥rk \ge r. For problems of (P2), close to the boundary of the region where the constant graphon is optimal, the upper-tail problem for regular graphs has a unique optimal graphon, which is bipodal.

Background

For a positive integer nn, write [n]:={1,2,…,n}[n] := \{1, 2, \ldots, n\}. Throughout the paper, a graph is an undirected, finite, simple graph (no self-loops and no multiple edges). For a graph GG, we write V(G)V(G) and E(G)E(G) for its vertex and edge sets, and let v(G):=∣V(G)∣v(G) := |V(G)| and e(G):=∣E(G)∣e(G) := |E(G)|. We use standard notation for familiar graphs: KnK_n denotes the complete graph on nn vertices (i.e., V(Kn)=[n]V(K_n) = [n] and E(Kn)={{i,j}:i,j∈[n],i≠j}E(K_n) = \{\{i, j\} : i, j \in[n], i \ne j\}), K1,nK_{1,n} denotes the complete bipartite graph with part sizes 11 and nn (i.e., V(K1,n)=[n+1]V(K_{1,n}) = [n + 1] and E(K1,n)={{1,i}:2≤i≤n+1}E(K_{1,n}) = \{\{1, i\} : 2 \le i \le n + 1\}), and CnC_n denotes the cycle on nn vertices (i.e., V(Cn)=[n]V(C_n) = [n] and E(Cn)={{i,i+1}:1≤i≤n−1}∪{{n,1}}E(C_n) = \{\{i, i + 1\} : 1 \le i \le n - 1\} \cup\{\{n, 1\}\}).

Let HH and GG be graphs. A homomorphism from HH to GG is a map ϕ:V(H)→V(G)\phi: V(H) \to V(G) that preserves adjacency, i.e., {ϕ(u),ϕ(v)}∈E(G)\{\phi(u), \phi(v)\} \in E(G) for every {u,v}∈E(H)\{u, v\} \in E(H). The homomorphism density from HH to GG, denoted t(H,G)t(H, G), is the probability that a uniformly random map ϕ:V(H)→V(G)\phi: V(H) \to V(G) is a homomorphism. Equivalently,

t(H,G):=1v(G)v(H)∑ϕ:V(H)→V(G)∏{u,v}∈E(H)I[{ϕ(u),ϕ(v)}∈E(G)].(2)t(H,G) := \frac{1}{v(G)^{v(H)}} \sum_{\phi:V(H)\to V(G)} \prod_{\{u,v\}\in E(H)} \mathbb{I}[\{\phi(u),\phi(v)\}\in E(G)] . \tag*{(2)}

where I[⋅]\mathbb{I}[\cdot] is the indicator function. Homomorphism densities are a natural language for extremal graph problems: they are size-normalised statistics of fixed patterns, so objectives and constraints are comparable across graphs of different sizes, and they are central to dense graph limit theory, quasirandomness, and regularity-based approximation [24].

A graphon WW is a symmetric measurable function W:[0,1]2→[0,1]W : [0, 1]^2 \to[0, 1]. Intuitively, WW can be viewed as the (probabilistic) adjacency matrix of a continuum graph with vertex set [0,1][0, 1]: W(x,y)W(x, y) is the probability of an edge between xx and yy. Graphons arise as limits of dense graphs: along any graph sequence (Gn)n∈N(G_n)_{n\in\mathbb{N}} whose homomorphism densities t(H,Gn)t(H, G_n) converge for every fixed graph HH with vertex set [v(H)][v(H)], there is a graphon WW with t(H,Gn)→t(H,W)t(H, G_n) \to t(H, W) for every HH with vertex set [v(H)][v(H)], where t(H,W)t(H, W) is the graphon homomorphism density of HH in WW defined by

t(H,W):=Ex1,…,xv(H)∼iidUnif⁡[0,1][∏{i,j}∈E(H)W(xi,xj)].(3)t(H,W) := \mathbb{E}_{x_1,\ldots,x_{v(H)}\mathrel{\overset{\mathrm{iid}}{\sim}}\operatorname{Unif}[0,1]}\left[\prod_{\{i,j\}\in E(H)} W(x_i,x_j)\right]. \tag*{(3)}

Conversely, every graphon arises in this way [26, 24]. Familiar discrete structure is reflected in WW: balanced complete bipartite graphs converge to the two-block graphon equal to 11 on the off-diagonal blocks and 00 on the diagonal blocks; an Erdős–Rényi G(n,q)G(n,q) converges to the constant graphon W≡qW \equiv q; a stochastic block model converges to a multi-block graphon whose blocks correspond to the communities.

Graphons provide a common language for both problem families studied in this paper: the objective and constraints in each involve graph homomorphism densities t(H,W)t(H, W) or closely related graphon integrals, and the structure of the optimal graphons is the central object of interest. The first family arises from extremal graph theory, where optimising over graphs is equivalent to optimising the corresponding asymptotic finite-graph problem [24]; the second arises from the large deviation theory of dense random graphs. We describe each in turn. Constrained density minimisation. The first problem family is concerned with minimising the homomorphism density of a fixed graph HH subject to a fixed edge density pp. To state the asymptotic problem formally, we phrase it in terms of graph sequences:

inf⁡{lim inf⁡n→∞t(H,Gn) | (Gn) is a graph sequence with v(Gn)→∞ and t(K2,Gn)→p}.(4)\inf\left\{ \liminf_{n\to\infty} t(H,G_n) \,\middle|\, (G_n)\text{ is a graph sequence with }v(G_n)\to\infty\text{ and }t(K_2,G_n)\to p \right\}. \tag*{(4)}

By the graph-limit theory [24], this equals min⁡W:t(K2,W)=pt(H,W)\min_{W:t(K_2,W)=p} t(H,W), the graphon problem our method optimises directly. It generalises Turán’s theorem [47] and the Erdős–Stone–Simonovits theorem [13, 12]. These classical results in extremal graph theory say that for every HH with at least one edge and p≤1−1/(χ(H)−1)p\leq1-1/(\chi(H)-1), where χ(H)\chi(H) is the chromatic number of HH, the optimum is 0. But for p>1−1/(χ(H)−1)p>1-1/(\chi(H)-1), the problem is much harder. It is completely solved only for cliques: H=KrH=K_r for all r≥3r\geq3 [42], with earlier results for r=3r=3 [40] and r=4r=4 [32]. For C5C_5, the minimiser is known only at the special values p=1−1/kp=1-1/k (kk a positive integer) [4].

Variational problem from large deviation theory. The large deviation theory of dense random graphs addresses two related questions: at what exponential rate does the Erdős–Rényi random graph G(n,q)G(n,q) have an atypically large or small homomorphism density, and what does the graph typically look like when such a rare event occurs? These questions are of fundamental interest in probability theory and combinatorics, and they carry information-theoretic structure that is natural from an ML perspective: the Chatterjee–Varadhan framework reduces both questions to a single constrained optimisation over graphons whose objective is an averaged KL divergence [8].

References

  1. [1]Boris Alexeev, Kevin Barreto, Yanyang Li, Jared Duker Lichtman, Liam Price, Jibran Iqbal Shah, Quanyu Tang, and Terence Tao. Primitive sets and von Mangoldt chains: Erdős problem #1196 and beyond, 2026. URL https://arxiv.org/abs/2605.00301.
  2. [2]Ali Azizpour, Nicolas Zilberstein, and Santiago Segarra. Scalable implicit graphon learning. In Proceedings of the 28th International Conference on Artificial Intelligence and Statistics, volume 258 of Proceedings of Machine Learning Research, pages 3952–3960. PMLR, 2025. URL https://proceedings.mlr.press/v258/azizpour25a.html.arxiv.org/abs/2410.17464
  3. [3]Shaojie Bai, J. Zico Kolter, and Vladlen Koltun. Deep equilibrium models. In Advances in Neural Information Processing Systems, volume 32, 2019. URL https://proceedings.neurips.cc/paper/2019/hash/01386bd6d8e091c2ab4c7c7de644d37b—Abstract.html.
  4. [4]Patrick Bennett, Andrzej Dudek, Bernard Lidický, and Oleg Pikhurko. Minimizing the number of 5-cycles in graphs with given edge-density. Combinatorics, Probability and Computing, 29 (1):44–67, 2020. doi: 10.1017/S0963548319000257.DOI
  5. [5]Béla Bollobás. Relations between sets of complete subgraphs. In C. St. J. A. Nash-Williams and J. Sheehan, editors, Proceedings of the Fifth British Combinatorial Conference, pages 79–84, Winnipeg, 1976. Utilitas Mathematica.
  6. [6]Christian Borgs, Jennifer Chayes, László Lovász, Vera T. Sós, and Katalin Vesztergombi. Counting graph homomorphisms. In Topics in Discrete Mathematics, pages 315–371. Springer, 2006. doi: 10.1007/3-540-33700-8_18.DOI
  7. [7]François Charton, Jordan S. Ellenberg, Adam Zsolt Wagner, and Geordie Williamson. PatternBoost: Constructions in mathematics with a little help from AI, 2024. URL https://arxiv.org/abs/2411.00566.
  8. [8]Sourav Chatterjee and S. R. S. Varadhan. The large deviation principle for the Erdős–Rényi random graph. European Journal of Combinatorics, 32(7):1000–1017, 2011. doi: 10.1016/j.ejc.2011.03.014.DOI
  9. [9]Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, and David K. Duvenaud. Neural ordinary differential equations. In Advances in Neural Information Processing Systems, volume 31, 2018. URL https://proceedings.neurips.cc/paper/2018/hash/69386f6bb1dfed68692a24c8686939b9-Abstract.html.arxiv.org/abs/1806.07366
  10. [10]Zhiqin Chen and Hao Zhang. Learning implicit fields for generative shape modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5939–5948, 2019. doi: 10.1109/CVPR.2019.00609.DOI
  11. [11]Alex Davies, Petar Veličković, Lars Buesing, Sam Blackwell, Daniel Zheng, Nenad Tomašev, Richard Tanburn, Peter Battaglia, Charles Blundell, András Juhász, Marc Lackenby, Geordie Williamson, Demis Hassabis, and Pushmeet Kohli. Advancing mathematics by guiding human intuition with AI. Nature, 600(7887):70–74, 2021. doi: 10.1038/s41586-021-04086-x.DOI
  12. [12]Paul Erdős and Miklós Simonovits. A limit theorem in graph theory. Studia Scientiarum Mathematicarum Hungarica, 1:51–57, 1966.
  13. [13]Paul Erdős and A. H. Stone. On the structure of linear graphs. Bulletin of the American Mathematical Society, 52:1087–1091, 1946.
  14. [14]Victor Falgas-Ravry and Emil R. Vaughan. Applications of the semi-definite method to the Turán density problem for 3-graphs. Combinatorics, Probability and Computing, 22(1):21–54, 2013. doi: 10.1017/S0963548312000508.
  15. [15]David C. Fisher. Lower bounds on the number of triangles in a graph. Journal of Graph Theory, 13(4):505–512, 1989. doi: 10.1002/jgt.3190130411.DOI
  16. [16]A. W. Goodman. On sets of acquaintances and strangers at any party. The American Mathematical Monthly, 66(9):778–783, 1959. doi: 10.1080/00029890.1959.11989408.DOI
  17. [17]Yang-Hui He, Kyu-Hwan Lee, Thomas Oliver, and Alexey Pozdnyakov. Murmurations of elliptic curves. Experimental Mathematics, 34(3):528–540, 2025. doi: 10.1080/10586458.2024.2382361.DOI
  18. [18]Yichen Huang and Lin F. Yang. Winning gold at IMO 2025 with a model-agnostic verification-and-refinement pipeline, 2025. URL https://arxiv.org/abs/2507.15855.
  19. [19]Thomas Hubert, Rishi Mehta, Laurent Sartran, Miklós Z. Horváth, Goran Žužić, Eric Wieser, Aja Huang, Julian Schrittwieser, Yannick Schroeker, Hussain Masoom, Ottavia Bertolli, Tom Zahavy, Amol Mandhane, Jessica Yung, Juliya Beloshapka, Borja Ibarz, Vivek Veeriah, Lei Yu, Oliver Nash, Paul Lezeau, Salvatore Mercuri, Calle Sönne, Bhavik Mehta, Alex Davies, Daniel Zheng, Fabian Pedregosa, Yin Li, Ingrid von Glehn, Mark Rowland, Samuel Albanie, Ameya Velingker, Simon Schmitt, Edward Lockhart, Edward Hughes, Henryk Michalewski, Nicolas Sonnerat, Demis Hassabis, Pushmeet Kohli, and David Silver. Olympiad-level formal mathematical reasoning with reinforcement learning. Nature, 651(8106):607–613, 2026. doi: 10.1038/s41586-025-09833-y.DOI
  20. [20]Seonghyuk Im, Taeyoung Kim, and Hongseok Yang. Goodman-type lower bounds for odd cycles I: The dense regime, 2026. URL https://arxiv.org/abs/2610.18277.
  21. [21]Albert Qiaochu Jiang, Sean Welleck, Jin Peng Zhou, Timothée Lacroix, Jiacheng Liu, Wenda Li, Mateja Jamnik, Guillaume Lample, and Yuhuai Wu. Draft, sketch, and prove: Guiding formal theorem provers with informal proofs. In Proceedings of the 11th International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=SMa9EAovKMC.arxiv.org/abs/2210.12283
  22. [22]Sangho Lim, Seonghyuk Im, Taeyoung Kim, Kyeongsik Nam, and Hongseok Yang. Bipodal optimizers in the upper-tail variational problem for regular subgraph densities, 2026. URL https://arxiv.org/abs/2609.15222.
  23. [23]Ilya Loshchilov and Frank Hutter. SGDR: Stochastic gradient descent with warm restarts. In Proceedings of the 5th International Conference on Learning Representations, 2017. URL https://openreview.net/forum?id=Skq89Scxx.arxiv.org/abs/1608.03983
  24. [24]László Lovász. Large Networks and Graph Limits, volume 60 of American Mathematical Society Colloquium Publications. American Mathematical Society, Providence, RI, 2012. ISBN 978-0-8218-9085-1. doi: 10.1090/coll/060.DOI
  25. [25]László Lovász and Miklós Simonovits. On the number of complete subgraphs of a graph II. In Studies in Pure Mathematics: To the Memory of Paul Turán, pages 459–495. Birkhäuser, Basel, 1983. doi: 10.1007/978-3-0348-5438-2_41.DOI
  26. [26]László Lovász and Balázs Szegedy. Limits of dense graph sequences. Journal of Combinatorial Theory, Series B, 96(6):933–957, 2006. doi: 10.1016/j.jctb.2006.05.002.DOI
  27. [27]Eyal Lubetzky and Yufei Zhao. On replica symmetry of large deviations in random graphs. Random Structures & Algorithms, 47(1):109–146, 2015. doi: 10.1002/rsa.20536.DOI
  28. [28]Willem Mantel. Vraagstuk XXVIII. Wiskundige Opgaven met de Oplossingen, 10:60–61, 1907.
  29. [29]Abbas Mehrabian, Ankit Anand, Hyunjik Kim, Nicolas Sonnerat, Matej Balog, Gheorghe Comanici, Tudor Berariu, Andrew Lee, Anian Ruoss, Anna Bulanova, Daniel Toyama, Sam Blackwell, Bernardino Romera-Paredes, Petar Veličković, Laurent Orseau, Joonkyung Lee, Anurag Murty Naredla, Doina Precup, and Adam Zsolt Wagner. Finding increasingly large extremal graphs with AlphaZero and tabu search. In Proceedings of the 33rd International Joint Conference on Artificial Intelligence, pages 6985–6993, 2024. doi: 10.24963/ijcai.2024/772.
  30. [30]Lars Mescheder, Michael Oechsle, Michael Niemeyer, Sebastian Nowozin, and Andreas Geiger. Occupancy networks: Learning 3D reconstruction in function space. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4460–4470, 2019. doi: 10.1109/CVPR.2019.00459.DOI
  31. [31]Konrad Mundinger, Max Zimmer, Aldo Kiem, Christoph Spiegel, and Sebastian Pokutta. Neural discovery in mathematics: Do machines dream of colored planes? In Proceedings of the 42nd International Conference on Machine Learning, volume 267 of Proceedings of Machine Learning Research, pages 45236–45255. PMLR, 2025. URL https://proceedings.mlr.press/v267/mundinger25a.html.arxiv.org/abs/2501.18527
  32. [32]Vladimir Nikiforov. The number of cliques in graphs of given order and size. Transactions of the American Mathematical Society, 363(3):1599–1618, 2011. doi: 10.1090/S0002-9947-2010-05189-X.DOI
  33. [33]Alexander Novikov, Ngân Vũ, Marvin Eisenberger, Emilien Dupont, Po-Sen Huang, Adam Zsolt Wagner, Sergey Shirobokov, Borislav Kozlovskii, Francisco J. R. Ruiz, Abbas Mehrabian, M. Pawan Kumar, Abigail See, Swarat Chaudhuri, George Holland, Alex Davies, Sebastian Nowozin, Pushmeet Kohli, and Matej Balog. AlphaEvolve: A coding agent for scientific and algorithmic discovery, 2025. URL https://arxiv.org/abs/2506.13131.
  34. [34]Olaf Parczyk, Sebastian Pokutta, Christoph Spiegel, and Tibor Szabó. New Ramsey multiplicity bounds and search heuristics. Foundations of Computational Mathematics, 25(5):1777–1814, 2025. doi: 10.1007/s10208-024-09675-6.DOI
  35. [35]Jeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, and Steven Lovegrove. DeepSDF: Learning continuous signed distance functions for shape representation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 165–174, 2019. doi: 10.1109/CVPR.2019.00025.DOI
  36. [36]Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, and Aaron Courville. FiLM: Visual reasoning with a general conditioning layer. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018. doi: 10.1609/aaai.v32i1.11671.DOI
  37. [37]Oleg Pikhurko and Alexander Razborov. Asymptotic structure of graphs with the minimum number of triangles. Combinatorics, Probability and Computing, 26(1):138–160, 2017. doi: 10.1017/S0963548316000110.DOI
  38. [38]Stanislav Polu, Jesse Michael Han, Kunhao Zheng, Mantas Baksys, Igor Babuschkin, and Ilya Sutskever. Formal mathematics statement curriculum learning. In Proceedings of the 11th International Conference on Learning Representations, 2023. URL https://openreview.net/forum?id=P7G-8dmSh4.arxiv.org/abs/2202.01344
  39. [39]Alexander A. Razborov. Flag algebras. Journal of Symbolic Logic, 72(4):1239–1282, 2007. doi: 10.2178/jsl/1203350785.DOI
  40. [40]Alexander A. Razborov. On the minimal density of triangles in graphs. Combinatorics, Probability and Computing, 17(4):603–618, 2008. doi: 10.1017/S0963548308009085.DOI
  41. [41]Alexander A. Razborov. Flag algebras: An interim report. In The Mathematics of Paul Erdős II, pages 207–232. Springer, New York, NY, 2013. doi: 10.1007/978-1-4614-7254-4_16.DOI
  42. [42]Christian Reiher. The clique density theorem. Annals of Mathematics, 184(3):683–707, 2016. doi: 10.4007/annals.2016.184.3.1.DOI
  43. [43]Bernardino Romera-Paredes, Mohammadamin Barekatain, Alexander Novikov, Matej Balog, M. Pawan Kumar, Emilien Dupont, Francisco J. R. Ruiz, Jordan S. Ellenberg, Pengming Wang, Omar Fawzi, Pushmeet Kohli, and Alhussein Fawzi. Mathematical discoveries from program search with large language models. Nature, 625(7995):468–475, 2024. doi: 10.1038/s41586-023-06924-6.
  44. [44]Alexander Sidorenko. A correlation inequality for bipartite graphs. Graphs and Combinatorics, 9(2–4):201–204, 1993. doi: 10.1007/BF02988307.DOI
  45. [45]Matthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, and Ren Ng. Fourier features let networks learn high frequency functions in low dimensional domains. In Advances in Neural Information Processing Systems, volume 33, 2020. URL https://proceedings.neurips.cc/paper/2020/hash/55053683268957697aa39fba6f231c68-Abstract.html.
  46. [46]Trieu H. Trinh, Yuhuai Wu, Quoc V. Le, He He, and Thang Luong. Solving olympiad geometry without human demonstrations. Nature, 625(7995):476–482, 2024. doi: 10.1038/s41586-023-06747-5.DOI
  47. [47]Pál Turán. Eine Extremalaufgabe aus der Graphentheorie. Matematikai és Fizikai Lapok, 48:436–452, 1941.
  48. [48]Adam Zsolt Wagner. Constructions in combinatorics via neural networks, 2021. URL https://arxiv.org/abs/2104.14516.
  49. [49]Yuhuai Wu, Albert Qiaochu Jiang, Wenda Li, Markus Rabe, Charles Staats, Mateja Jamnik, and Christian Szegedy. Autoformalization with large language models. In Advances in Neural Information Processing Systems, volume 35, 2022. URL https://proceedings.neurips.cc/paper_files/paper/2022/hash/d0c6bc641a56bebee9d985b937037367-Abstract-Conference.html.arxiv.org/abs/2205.12615
  50. [50]Xinyue Xia, Gal Mishne, and Yusu Wang. Implicit graphon neural representation. In Proceedings of the 26th International Conference on Artificial Intelligence and Statistics, volume 206 of Proceedings of Machine Learning Research, pages 10619–10634. PMLR, 2023. URL https://proceedings.mlr.press/v206/xia23b.html.arxiv.org/abs/2211.03329

Paper details

vlnc:W_tc9q66ee
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 2

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

Not recorded for this paper

View statement
Looking for related papers…
Contents