The Lovász Theta Function for Random Regular Graphs and Community Detection in the Hard Regime

We derive upper and lower bounds on the degree d for which the Lovász θ function, or equivalently sum-of-squares proofs with degree two, can refute the existence of a k-coloring in random regular graphs Gn,d . We show that this type of refutation fails well above the k-colorability transition, and in particular everywhere below the Kesten-Stigum threshold. Œis is consistent with the conjecture that refuting k-colorability, or distinguishing Gn,d from the planted coloring model, is hard in this region. Our results also apply to the disassortative case of the stochastic block model, adding evidence to the conjecture that there is a regime where community detection is computationally hard even though it is information-theoretically possible. Using orthogonal polynomials, we also provide explicit upper bounds on θ(G) for regular graphs of a given girth, which may be of independent interest.

[1]  Tomasz Luczak.  A note on the sharp concentration of the chromatic number of random graphs , 1991, Comb..

[2]  Emmanuel Abbe,et al.  Community Detection in General Stochastic Block models: Fundamental Limits and Efficient Algorithms for Recovery , 2015, 2015 IEEE 56th Annual Symposium on Foundations of Computer Science.

[3]  Andrea Montanari,et al.  Gibbs states and the set of solutions of random constraint satisfaction problems , 2006, Proceedings of the National Academy of Sciences.

[4]  Paolo Barucca,et al.  Spectral partitioning in random regular blockmodels , 2016, ArXiv.

[5]  Yurii Nesterov,et al.  Squared Functional Systems and Optimization Problems , 2000 .

[6]  Jean B. Lasserre,et al.  Global Optimization with Polynomials and the Problem of Moments , 2000, SIAM J. Optim..

[7]  P. Bickel,et al.  A nonparametric view of network models and Newman–Girvan and other modularities , 2009, Proceedings of the National Academy of Sciences.

[8]  Cristopher Moore,et al.  The Computer Science and Physics of Community Detection: Landscapes, Phase Transitions, and Hardness , 2017, Bull. EATCS.

[9]  Emmanuel Abbe,et al.  Detection in the stochastic block model with multiple clusters: proof of the achievability conjectures, acyclic BP, and the information-computation gap , 2015, ArXiv.

[10]  Ioana Dumitriu,et al.  Recovery and Rigidity in a Regular Stochastic Block Model , 2016, SODA.

[11]  Cristopher Moore,et al.  Asymptotic analysis of the stochastic block model for modular networks and its algorithmic applications , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  Alexandra Kolla,et al.  Multisection in the Stochastic Block Model using Semidefinite Programming , 2015, ArXiv.

[13]  H. Kesten,et al.  Limit theorems for decomposable multi-dimensional Galton-Watson processes , 1967 .

[14]  N. Wormald.  Models of random regular graphs , 2010 .

[15]  Emmanuel Abbe,et al.  Community detection and stochastic block models: recent developments , 2017, Found. Trends Commun. Inf. Theory.

[16]  J. Krivine,et al.  Anneaux préordonnés , 1964 .

[17]  Ryan O'Donnell,et al.  Sum of squares lower bounds for refuting any CSP , 2017, STOC.

[18]  Assaf Naor,et al.  The two possible values of the chromatic number of a random graph , 2004, STOC '04.

[19]  Emmanuel Abbe,et al.  Achieving the KS threshold in the general stochastic block model with linearized acyclic belief propagation , 2016, NIPS.

[20]  N. Z. Shor.  An approach to obtaining global extremums in polynomial mathematical programming problems , 1987 .

[21]  Joel Friedman,et al.  A proof of Alon's second eigenvalue conjecture and related problems , 2004, ArXiv.

[22]  Elchanan Mossel,et al.  Spectral redemption in clustering sparse networks , 2013, Proceedings of the National Academy of Sciences.

[23]  Pravesh Kothari,et al.  A Nearly Tight Sum-of-Squares Lower Bound for the Planted Clique Problem , 2016, 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS).

[24]  P. Parrilo.  Structured semidefinite programs and semialgebraic geometry methods in robustness and optimization , 2000 .

[25]  H. Kesten,et al.  Additional Limit Theorems for Indecomposable Multidimensional Galton-Watson Processes , 1966 .

[26]  Florent Krzakala,et al.  Hiding Quiet Solutions in Random Constraint Satisfaction Problems , 2009, Physical review letters.

[27]  Laurent Massoulié,et al.  Non-backtracking Spectrum of Random Graphs: Community Detection and Non-regular Ramanujan Graphs , 2014, 2015 IEEE 56th Annual Symposium on Foundations of Computer Science.

[28]  Cristopher Moore,et al.  The Chromatic Number of Random Regular Graphs , 2004, APPROX-RANDOM.

[29]  Laurent Massoulié,et al.  Community detection thresholds and the weak Ramanujan property , 2013, STOC.

[30]  Grant Schoenebeck,et al.  Linear Level Lasserre Lower Bounds for Certain k-CSPs , 2008, 2008 49th Annual IEEE Symposium on Foundations of Computer Science.

[31]  Amin Coja-Oghlan.  The Lovász Number of Random Graphs , 2003, RANDOM-APPROX.

[32]  N. Wormald,et al.  On the chromatic number of random d-regular graphs , 2008, 0812.2937.

[33]  Mark E. J. Newman,et al.  Equitable random graphs , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[34]  Amin Coja-Oghlan,et al.  Charting the Replica Symmetric Phase , 2017, APPROX-RANDOM.

[35]  Avi Wigderson,et al.  Sum-of-squares Lower Bounds for Planted Clique , 2015, STOC.

[36]  Elchanan Mossel,et al.  Reconstruction and estimation in the planted partition model , 2012, Probability Theory and Related Fields.

[37]  Emmanuel Abbe,et al.  Crossing the KS threshold in the stochastic block model with information theory , 2016, 2016 IEEE International Symposium on Information Theory (ISIT).

[38]  Elchanan Mossel,et al.  A Spectral Approach to Analysing Belief Propagation for 3-Colouring , 2007, Combinatorics, Probability and Computing.

[39]  Prasad Raghavendra,et al.  On the Integrality Gap of Degree-4 Sum of Squares for Planted Clique , 2016, SODA.

[40]  Bruce E. Hajek,et al.  Achieving Exact Cluster Recovery Threshold via Semidefinite Programming: Extensions , 2015, IEEE Transactions on Information Theory.

[41]  N. Alon,et al.  Non-backtracking random walks mix faster , 2006, math/0610550.

[42]  Elchanan Mossel,et al.  Consistency Thresholds for the Planted Bisection Model , 2014, STOC.

[43]  Amin Coja-Oghlan,et al.  Chasing the K-Colorability Threshold , 2013, 2013 IEEE 54th Annual Symposium on Foundations of Computer Science.

[44]  David Steurer,et al.  Sum-of-squares proofs and the quest toward optimal algorithms , 2014, Electron. Colloquium Comput. Complex..

[45]  Andrea Montanari,et al.  Improved Sum-of-Squares Lower Bounds for Hidden Clique and Hidden Submatrix Problems , 2015, COLT.

[46]  Ryan O'Donnell,et al.  How to Refute a Random CSP , 2015, 2015 IEEE 56th Annual Symposium on Foundations of Computer Science.

[47]  Bruce E. Hajek,et al.  Achieving exact cluster recovery threshold via semidefinite programming , 2015, 2015 IEEE International Symposium on Information Theory (ISIT).

[48]  Florent Krzakala,et al.  Information-theoretic thresholds from the cavity method , 2016, STOC.

[49]  Emmanuel Abbe,et al.  Exact Recovery in the Stochastic Block Model , 2014, IEEE Transactions on Information Theory.

[50]  Jess Banks,et al.  Information-theoretic thresholds for community detection in sparse networks , 2016, COLT.

[51]  Elchanan Mossel,et al.  A Proof of the Block Model Threshold Conjecture , 2013, Combinatorica.

[52]  Elchanan Mossel,et al.  Belief propagation, robust reconstruction and optimal recovery of block models , 2013, COLT.