# Computational Barriers to Estimation from Low-Degree Polynomials

@article{Schramm2020ComputationalBT, title={Computational Barriers to Estimation from Low-Degree Polynomials}, author={Tselil Schramm and Alexander S. Wein}, journal={ArXiv}, year={2020}, volume={abs/2008.02269} }

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

#### Topics from this paper

#### 9 Citations

Hypothesis testing with low-degree polynomials in the Morris class of exponential families

- Computer Science, Mathematics
- COLT
- 2021

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

- Computer Science, Mathematics
- ArXiv
- 2021

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?

- Computer Science, Mathematics
- COLT
- 2021

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

- Computer Science, Physics
- ArXiv
- 2021

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

- Mathematics, Computer Science
- ArXiv
- 2020

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

- Mathematics, Computer Science
- ArXiv
- 2020

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

- Computer Science
- 2021

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 from… Expand

Is the space complexity of planted clique recovery the same as that of detection?

- Computer Science, Mathematics
- ITCS
- 2021

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

- Computer Science, Mathematics
- COLT
- 2021

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

#### References

SHOWING 1-10 OF 96 REFERENCES

High-dimensional estimation via sum-of-squares proofs

- Computer Science, Mathematics
- Proceedings of the International Congress of Mathematicians (ICM 2018)
- 2019

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

- Computer Science, Mathematics
- 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS)
- 2017

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

- 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

- Computer Science, Mathematics
- 2014

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

- Mathematics
- 2017

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 that… Expand

Sparse CCA: Adaptive Estimation and Computational Barriers

- Mathematics
- 2014

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 originated… Expand

Efficient Bayesian Estimation from Few Samples: Community Detection and Related Problems

- Mathematics, Computer Science
- 2017 IEEE 58th Annual Symposium on Foundations of Computer Science (FOCS)
- 2017

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

- Computer Science, Mathematics
- ArXiv
- 2018

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

- Computer Science, Mathematics
- COLT
- 2018

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

- Computer Science, Mathematics
- NIPS
- 2011

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