Tight Lower Bounds for Planted Clique in the Degree-4 SOS Program

نویسندگان

  • Prasad Raghavendra
  • Tselil Schramm
چکیده

We give a lower bound of Ω̃( √ n) for the degree-4 Sum-of-Squares SDP relaxation for the planted clique problem. Specifically, we show that on an Erdös-Rényi graph G(n, 1 2 ), with high probability there is a feasible point for the degree-4 SOS relaxation of the clique problem with an objective value of Ω̃( √ n), so that the program cannot distinguish between a random graph and a random graph with a planted clique of size Õ( √ n). This bound is tight. We build on the works of Deshpande and Montanari and Meka et al., who give lower bounds of Ω̃(n) and Ω̃(n) respectively. We improve on their results by making a perturbation to the SDP solution proposed in their work, then showing that this perturbation remains PSD as the objective value approaches Ω̃(n). In an independent work, Hopkins, Kothari and Potechin [HKP15] have obtained a similar lower bound for the degree-4 SOS relaxation. UC Berkeley, [email protected]. Supported by NSF Career Award, NSF CCF-1407779 and the Alfred. P. Sloan Fellowship. UC Berkeley, [email protected]. Supported by an NSF Graduate Research Fellowship (NSF award no 1106400).

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

SoS and Planted Clique: Tight Analysis of MPW Moments at all Degrees and an Optimal Lower Bound at Degree Four

The problem of finding large cliques in random graphs and its “planted" variant, where one wants to recover a clique of size ω log (n) added to an Erdős-Rényi graph G ∼ G(n, 2 ), have been intensely studied. Nevertheless, existing polynomial time algorithms can only recover planted cliques of size ω = Ω( √ n). By contrast, information theoretically, one can recover planted cliques so long as ω ...

متن کامل

Improved Sum-of-Squares Lower Bounds for Hidden Clique and Hidden Submatrix Problems

Given a large data matrix A ∈ Rn×n, we consider the problem of determining whether its entries are i.i.d. from some known marginal distribution Aij ∼ P0, or instead A contains a principal submatrix AQ,Q whose entries have marginal distribution Aij ∼ P1 6= P0. As a special case, the hidden (or planted) clique problem is finding a planted clique in an otherwise uniformly random graph. Assuming un...

متن کامل

Tight SoS-Degree Bounds for Approximate Nash Equilibria

Nash equilibria always exist, but are widely conjectured to require time to find that is exponential in the number of strategies, even for two-player games. By contrast, a simple quasi-polynomial time algorithm, due to Lipton, Markakis and Mehta (LMM), can find approximate Nash equilibria, in which no player can improve their utility by more than by changing their strategy. The LMM algorithm ca...

متن کامل

ar X iv : 1 50 4 . 01 65 6 v 1 [ cs . C C ] 7 A pr 2 01 5 Tight Size - Degree Bounds for Sums - of - Squares Proofs ∗

We exhibit families of 4-CNF formulas over n variables that have sums-of-squares (SOS) proofs of unsatisfiability of degree (a.k.a. rank) d but require SOS proofs of size n for values of d = d(n) from constant all the way up to n for some universal constant δ. This shows that the n running time obtained by using the Lasserre semidefinite programming relaxations to find degree-d SOS proofs is op...

متن کامل

Sum-of-Squares Lower Bounds for Sparse PCA

This paper establishes a statistical versus computational trade-off for solving a basic high-dimensional machine learning problem via a basic convex relaxation method. Specifically, we consider the Sparse Principal Component Analysis (Sparse PCA) problem, and the family of Sum-of-Squares (SoS, aka Lasserre/Parillo) convex relaxations. It was well known that in large dimension p, a planted k-spa...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1507.05136  شماره 

صفحات  -

تاریخ انتشار 2015