arXiv subjects

Brice Huang

Publications and source records attributed to Brice Huang.

26 records · Page 2Linked to original sources

arXiv2022

Tight Lipschitz Hardness for Optimizing Mean Field Spin Glasses

We study the problem of algorithmically optimizing the Hamiltonian $H_N$ of a spherical or Ising mixed $p$-spin glass. The maximum asymptotic value $\mathsf{OPT}$ of $H_N/N$ is characterized by a variational principle known as the Parisi formula, proved first by Talagrand and in more generality by Panchenko. Recently developed approximate message passing algorithms efficiently optimize $H_N/N$ up to a value $\mathsf{ALG}$ given by an extended Parisi formula, which minimizes over a larger space of functional order parameters. These two objectives are equal for spin glasses exhibiting a no overlap gap property. However, $\mathsf{ALG} < \mathsf{OPT}$ can also occur, and no efficient algorithm producing an objective value exceeding $\mathsf{ALG}$ is known. We prove that for mixed even $p$-spin models, no algorithm satisfying an overlap concentration property can produce an objective larger than $\mathsf{ALG}$ with non-negligible probability. This property holds for all algorithms with suitably Lipschitz dependence on the disorder coefficients of $H_N$. It encompasses natural formulations of gradient descent, approximate message passing, and Langevin dynamics run for bounded time and in particular includes the algorithms achieving $\mathsf{ALG}$ mentioned above. To prove this result, we substantially generalize the overlap gap property framework introduced by Gamarnik and Sudan to arbitrary ultrametric forbidden structures of solutions.

math.PR↗

arXiv2022

Threshold for Detecting High Dimensional Geometry in Anisotropic Random Geometric Graphs

In the anisotropic random geometric graph model, vertices correspond to points drawn from a high-dimensional Gaussian distribution and two vertices are connected if their distance is smaller than a specified threshold. We study when it is possible to hypothesis test between such a graph and an Erdős-Rényi graph with the same edge probability. If $n$ is the number of vertices and $α$ is the vector of eigenvalues, Eldan and Mikulincer show that detection is possible when $n^3 \gg (\|α\|_2/\|α\|_3)^6$ and impossible when $n^3 \ll (\|α\|_2/\|α\|_4)^4$. We show detection is impossible when $n^3 \ll (\|α\|_2/\|α\|_3)^6$, closing this gap and affirmatively resolving the conjecture of Eldan and Mikulincer.

math.ST↗

arXiv2021

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 assignments exist with high probability up to clause density $m/n = 2^k \log 2 - \frac12 (\log 2 + 1) + o_k(1)$, while the best polynomial-time algorithm known, the Fix algorithm of Coja-Oghlan, finds a satisfying assignment at the much lower clause density $(1 - o_k(1)) 2^k \log k / k$. This prompts the question: is it possible to efficiently find a satisfying assignment at higher clause densities? We prove that the class of low degree polynomial algorithms cannot find a satisfying assignment at clause density $(1 + o_k(1)) κ^* 2^k \log k / k$ for a universal constant $κ^* \approx 4.911$. This class encompasses Fix, message passing algorithms including Belief and Survey Propagation guided decimation (with bounded or mildly growing number of rounds), and local algorithms on the factor graph. This is the first hardness result for any class of algorithms at clause density within a constant factor of that achieved by Fix. Our proof establishes and leverages a new many-way overlap gap property tailored to random $k$-SAT.

cs.CC↗

arXiv2021

De Finetti-Style Results for Wishart Matrices: Combinatorial Structure and Phase Transitions

A recent line of work has studied the relationship between the Wishart matrix $X^\top X$, where $X\in \mathbb{R}^{d\times n}$ has i.i.d. standard Gaussian entries, and the corresponding Gaussian matrix with independent entries above the diagonal. Jiang and Li (2015) and Bubeck et al. (2016) showed that these two matrix ensembles converge in total variation whenever $d/n^3\to \infty$, and Bubeck et al. (2016) showed this to be sharp. In this paper we aim to identify the precise threshold for $d$ in terms of $n$ for subsets of Wishart matrices to converge in total variation to independent Gaussians. It turns out that the combinatorial structure of the revealed entries, viewed as the adjacency matrix of a graph $G$, characterizes the distance from fully independent. Specifically, we show that the threshold for $d$ depends on the number of various small subgraphs in $G$. So, even when the number of revealed entries is fixed, the threshold can vary wildly depending on their configuration. Convergence of masked Wishart to independent Gaussians thus inherently involves an interplay between both probabilistic and combinatorial phenomena. Our results determine the sharp threshold for a large family of $G$, including Erdős-Rényi $G\sim \mathcal{G}(n,p)$ at all values $p\gtrsim n^{-2}\mathrm{polylog}(n)$. Our proof techniques are both combinatorial and information theoretic, which together allow us to carefully unravel the dependencies in the masked Wishart ensemble.

math.PR↗

arXiv2019

Cyclic Descents for General Skew Tableaux

A cyclic descent function on standard Young tableaux of size $n$ is a function that restricts to the usual descent function when $n$ is omitted, such that the number of standard Young tableaux of given shape with cyclic descent set $D\subset[n]$ is invariant under any modulo $n$ shift of $D$. The notion of cyclic descent was first studied for rectangles by Rhoades, and then generalized to certain families of skew shapes by Adin, Elizalde, and Roichman. Adin, Reiner, and Roichman proved that a skew shape has a cyclic descent map if and only if it is not a connected ribbon. Unfortunately, their proof is nonconstructive; until now, explicit cyclic descent maps are known only for small families of shapes. In this paper, we construct an explicit cyclic descent map for all shapes where this is possible. We thus provide a constructive proof of Adin, Reiner, and Roichman's result. Our construction of a cyclic descent map generalizes many of the constructions in the literature.

math.CO↗

arXiv2019

On the Local Geometry of Graphs in Terms of Their Spectra

In this paper we consider the relation between the spectrum and the number of short cycles in large graphs. Suppose $G_1, G_2, G_3, \ldots$ is a sequence of finite and connected graphs that share a common universal cover $T$ and such that the proportion of eigenvalues of $G_n$ that lie within the support of the spectrum of $T$ tends to 1 in the large $n$ limit. This is a weak notion of being Ramanujan. We prove such a sequence of graphs is asymptotically locally tree-like. This is deduced by way of an analogous theorem proved for certain infinite sofic graphs and unimodular networks, which extends results for regular graphs and certain infinite Cayley graphs.

math.CO↗

arXiv2019

An Upper Bound on the Number of $(132,213)$-Avoiding Cyclic Permutations

We show a $n^2 \cdot 2^{n/2}$ upper bound on the number of $(132,213)$ avoiding cyclic permutations. This is the first nontrivial upper bound on the number of such permutations. We also construct an algorithm to determine whether a $(132,213)$ avoiding permutation is cyclic that references only the permutation's layer lengths.

math.CO↗

arXiv2018

Convergence of Maximum Bisection Ratio of Sparse Random Graphs

We consider sequences of large sparse random graphs whose degree distribution approaches a limit with finite mean. This model includes both the random regular graphs and the Erdös-Renyi graphs of constant average degree. We prove that the maximum bisection ratio of such a graph sequence converges almost surely to a deterministic limit. We extend this result to so-called 2-spin spin glasses in the paramagnetic to ferromagnetic regime. Our work generalizes the graph interpolation method to some non-additive graph parameters.

math.PR↗