Corpus ID: 220968910

Computational Barriers to Estimation from Low-Degree Polynomials

  title={Computational Barriers to Estimation from Low-Degree Polynomials},
  author={Tselil Schramm and Alexander S. Wein},
One fundamental goal of high-dimensional statistics is to detect or recover structure from noisy data. In many cases, the data can be faithfully modeled by a planted structure (such as a low-rank matrix) perturbed by random noise. But even for these simple models, the computational complexity of estimation is sometimes poorly understood. A growing body of work studies low-degree polynomials as a proxy for computational complexity: it has been demonstrated in various settings that low-degree… Expand
Hypothesis testing with low-degree polynomials in the Morris class of exponential families
Low-degree polynomials appear to offer a tradeoff between robustness and strong performance fine-tuned to specific models, and may struggle with problems requiring an algorithm to first examine the input and then use some intermediate computation to choose from one of several inference subroutines. Expand
Reconstruction on Trees and Low-Degree Polynomials
The results clarify some of the limitations of low-degree polynomials vs. polynomial time algorithms for Bayesian estimation problems and complement recent work of Moitra, Mossel, and Sandon who studied the circuit complexity of Belief Propagation. Expand
Group testing and local search: is there a computational-statistical gap?
The fundamental limits of approximate recovery in the context of group testing is studied, and it is shown that a very simple local algorithm known as Glauber Dynamics does indeed succeed, and can be used to efficiently implement the well-known Smallest Satisfying Set (SSS) estimator. Expand
The Algorithmic Phase Transition of Random k-SAT for Low Degree Polynomials
It is shown that low degree polynomial algorithms can find a satisfying assignment at clause density (1−ok(1))2 k log k/k, matching Fix, and not at clausedensity (1 + ok(1), where κ∗ ≈ 4.911, the first sharp computational phase transition of random k-SAT for a class of algorithms. Expand
Optimal Low-Degree Hardness of Maximum Independent Set
It is shown that the class of low-degree polynomial algorithms can find independent sets of half-optimal size but no larger, improving upon a result of Gamarnik, Jagannath, and the author. Expand
Tensor Clustering with Planted Structures: Statistical Optimality and Computational Limits
The sharp boundaries of signal-to-noise ratio are identified: for which CHC and ROHC detection/recovery are statistically possible and it is proved that polynomial-time algorithms cannot solve these problems under the computational hardness conjectures of hypergraphic planted clique detection and hyperg Graphic planted dense subgraph (HPDS) recovery. Expand
Algorithmic Thresholds for Refuting Random Polynomial Systems
Consider a system of m polynomial equations {pi(x) = bi}i6m of degree D > 2 in ndimensional variable x ∈ Rn such that each coefficient of every pi and bis are chosen at random and independently fromExpand
Is the space complexity of planted clique recovery the same as that of detection?
The result suggests that there does exist an O(log n) space algorithm to recover cliques of size k = Omega(sqrt{n}), and provides evidence that the statistical-computational phenomena that hold for planted clique time complexity also holds for space complexity. Expand
Statistical Query Algorithms and Low-Degree Tests Are Almost Equivalent
This paper studies two of the most popular restricted computational models, the statistical query framework and low-degree polynomials, in the context of high-dimensional hypothesis testing, and finds that under mild conditions on the testing problem, the two classes of algorithms are essentially equivalent in power. Expand


High-dimensional estimation via sum-of-squares proofs
There is a growing body of work utilizing sum-of-squares proofs for recovering solutions to polynomial systems when the system is feasible, and a general technique referred to as pseudocalibration has been developed towards showing lower bounds on the degree of sum- of-Squares proofs. Expand
The Power of Sum-of-Squares for Detecting Hidden Structures
It is proved that for a wide class of planted problems, including refuting random constraint satisfaction problems, tensor and sparse PCA, densest-ksubgraph, community detection in stochastic block models, planted clique, and others, eigenvalues of degree-d matrix polynomials are as powerful as SoS semidefinite programs of degree d. Expand
Iterative estimation of constrained rank-one matrices in noise
  • S. Rangan, A. Fletcher
  • Computer Science, Mathematics
  • 2012 IEEE International Symposium on Information Theory Proceedings
  • 2012
This work considers the problem of estimating a rank-one matrix in Gaussian noise under a probabilistic model for the left and right factors of the matrix and proposes a simple iterative procedure that reduces the problem to a sequence of scalar estimation computations. Expand
Statistical and computational trade-offs in estimation of sparse principal components
It is shown that there is an effective sample size regime in which no randomised polynomial time algorithm can achieve the minimax optimal rate. Expand
Estimation of low-rank matrices via approximate message passing
Consider the problem of estimating a low-rank matrix when its entries are perturbed by Gaussian noise. If the empirical distribution of the entries of the spikes is known, optimal estimators thatExpand
Sparse CCA: Adaptive Estimation and Computational Barriers
Canonical correlation analysis is a classical technique for exploring the relationship between two sets of variables. It has important applications in analyzing high dimensional datasets originatedExpand
Efficient Bayesian Estimation from Few Samples: Community Detection and Related Problems
An efficient meta-algorithm for Bayesian inference problems based on low-degree polynomials, semidefinite programming, and tensor decomposition, inspired by recent lower bound constructions for sum-of-squares and related to the method of moments is proposed. Expand
Statistical and Computational Limits for Sparse Matrix Detection
A tight characterization of the statistical and computational limits for sparse matrix detection is provided, which precisely describe when achieving optimal detection is easy, hard, or impossible, respectively. Expand
Reducibility and Computational Lower Bounds for Problems with Planted Sparse Structure
This work introduces several new techniques to give a web of average-case reductions showing strong computational lower bounds based on the planted clique conjecture using natural problems as intermediates, including tight lower bounds for Planted Independent Set, Planted Dense Subgraph, Sparse Spiked Wigner, and Sparse PCA. Expand
Minimax Localization of Structural Information in Large Noisy Matrices
The SNR required by several computationally tractable procedures for biclustering including element-wise thresholding, column/row average thresholding and a convex relaxation approach to sparse singular vector decomposition is characterized. Expand