On the computational tractability of statistical estimation on amenable graphs

04/05/2019
by   Ahmed El Alaoui, et al.
0

We consider the problem of estimating a vector of discrete variables (θ_1,...,θ_n), based on noisy observations Y_uv of the pairs (θ_u,θ_v) on the edges of a graph G=([n],E). This setting comprises a broad family of statistical estimation problems, including group synchronization on graphs, community detection, and low-rank matrix estimation. A large body of theoretical work has established sharp thresholds for weak and exact recovery, and sharp characterizations of the optimal reconstruction accuracy in such models, focusing however on the special case of Erdös-Rényi-type random graphs. The single most important finding of this line of work is the ubiquity of an information-computation gap. Namely, for many models of interest, a large gap is found between the optimal accuracy achievable by any statistical method, and the optimal accuracy achieved by known polynomial-time algorithms. This gap is robust to small amounts of additional side information revealed about the θ_i's. How does the structure of the graph G affect this picture? Is the information-computation gap a general phenomenon or does it only apply to specific families of graphs? We prove that the picture is dramatically different for graph sequences converging to transitive amenable graphs (including, for instance, d-dimensional grids). We consider a model in which an arbitrarily small fraction of the vertex labels is revealed to the algorithm, and show that a linear-time algorithm can achieve reconstruction accuracy that is arbitrarily close to the information-theoretic optimum. We contrast this to the case of random graphs. Indeed, focusing on group synchronization on random regular graphs, we prove that the information-computation gap persists if a small amounts of additional side information revealed about the labels θ_i's.

READ FULL TEXT
research
06/09/2020

Phase retrieval in high dimensions: Statistical and computational phase transitions

We consider the phase retrieval problem of reconstructing a n-dimensiona...
research
12/14/2022

Equivalence of Approximate Message Passing and Low-Degree Polynomials in Rank-One Matrix Estimation

We consider the problem of estimating an unknown parameter vector θ∈ℝ^n,...
research
07/26/2018

Seeded Graph Matching via Large Neighborhood Statistics

We study a well known noisy model of the graph isomorphism problem. In t...
research
05/29/2022

Matching recovery threshold for correlated random graphs

For two correlated graphs which are independently sub-sampled from a com...
research
03/30/2021

Sharp Thresholds for a SIR Model on One-Dimensional Small-World Networks

We study epidemic spreading according to a Susceptible-Infectious-Recove...
research
07/14/2019

More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning

We consider the weakly supervised binary classification problem where th...
research
08/25/2010

Exact Synchronization for Finite-State Sources

We analyze how an observer synchronizes to the internal state of a finit...

Please sign up or login with your details

Forgot password? Click here to reset