arXiv research

New framework reduces sum-of-squares proof degree, speeding up clustering and robust moment estimation.

Estimation is the computational task of recovering a hidden parameter $x$ associated with a distribution $D_x$, given a measurement $y$ sampled from the distribution. High dimensional estimation problems arise naturally in statistics, machine learning, and complexity theory. Many high dimensional estimation problems ca…

Christoffel function characterizes the corruption a bounded-degree certificate cannot remove in robust halfspace learning.

This work improves graph inference using the degree-4 sum-of-squares hierarchy.

We study a statistical model for the tensor principal component analysis problem introduced by Montanari and Richard: Given a order-$3$ tensor $T$ of the form $T = τ\cdot v_0^{\otimes 3} + A$, where $τ\geq 0$ is a signal-to-noise ratio, $v_0$ is a unit vector, and $A$ is a random noise tensor, the goal is to recover th…

Sum-of-Squares lower bound shows NGCA requires more samples than known algorithms.

We obtain the first polynomial-time algorithm for exact tensor completion that improves over the bound implied by reduction to matrix completion. The algorithm recovers an unknown 3-tensor with $r$ incoherent, orthogonal components in $\mathbb R^n$ from $r\cdot \tilde O(n^{1.5})$ randomly observed entries of the tensor…

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 {\em Sparse Principal Component Analysis} (Sparse PCA) problem, and the family of {\em Sum-of-Squares} (SoS, aka Lasserre/…

Polynomial-time algorithm estimates mean with bounded covariance using differential privacy.

We develop efficient algorithms for estimating low-degree moments of unknown distributions in the presence of adversarial outliers. The guarantees of our algorithms improve in many cases significantly over the best previous ones, obtained in recent works of Diakonikolas et al, Lai et al, and Charikar et al. We also sho…

Survey on using low-degree polynomials to assess statistical tasks complexity.

Robustly clusters mixtures of Gaussians even with outliers.

New algorithms recover signals robustly against outliers and heavy-tailed noise.

New findings on tensor decomposition complexity, showing polynomial functions can estimate the largest component under certain conditions.

We study the problem of high-dimensional sparse mean estimation in the presence of an $ε$-fraction of adversarial outliers. Prior work obtained sample and computationally efficient algorithms for this task for identity-covariance subgaussian distributions. In this work, we develop the first efficient algorithms for rob…

New tools in nonlinear random matrices improve understanding of the Sum of Squares hierarchy.

These notes survey and explore an emerging method, which we call the low-degree method, for predicting and understanding statistical-versus-computational tradeoffs in high-dimensional inference problems. In short, the method posits that a certain quantity -- the second moment of the low-degree likelihood ratio -- gives…

Two spectral clustering methods for multi-layer networks are analyzed and compared.

Algorithm learns Gaussian mixtures robust to outliers.

New algorithms learn graph structures privately, matching best results.

New method finds global minima using function evaluations and kernel approximations.

We study tensor completion in the agnostic setting. In the classical tensor completion problem, we receive $n$ entries of an unknown rank-$r$ tensor and wish to exactly complete the remaining entries. In agnostic tensor completion, we make no assumption on the rank of the unknown tensor, but attempt to predict unknown …

Hilbert's 17th problem asks that whether every nonnegative polynomial can be a sum of squares of rational functions. It has been answered affirmatively by Artin. However, the question as to whether a given nonnegative polynomial is a sum of squares of polynomials is still a central question in real algebraic geometry. …

Polynomial-time algorithm finds planted hypercube vectors in Gaussian mixtures.

Paper solves outlier robust mean estimation near breakdown point.

In recent years, optimization theory has been greatly impacted by the advent of sum of squares (SOS) optimization. The reliance of this technique on large-scale semidefinite programs however, has limited the scale of problems to which it can be applied. In this paper, we introduce DSOS and SDSOS optimization as linear …

We propose an efficient meta-algorithm for Bayesian estimation problems that is based on low-degree polynomials, semidefinite programming, and tensor decomposition. The algorithm is inspired by recent lower bound constructions for sum-of-squares and related to the method of moments. Our focus is on sample complexity bo…

This work addresses privacy in Bayesian estimation, achieving near-optimal error rates.

New algorithm estimates edge density of random graphs robustly, achieving optimal breakdown point.

Polynomial-time algorithm estimates edge density of random graphs with privacy and robustness.

Given a large data matrix $A\in\mathbb{R}^{n\times n}$, we consider the problem of determining whether its entries are i.i.d. with some known marginal distribution $A_{ij}\sim P_0$, or instead $A$ contains a principal submatrix $A_{{\sf Q},{\sf Q}}$ whose entries have marginal distribution $A_{ij}\sim P_1\neq P_0$. As …

Paper introduces a new kernel model for PSD-valued functions with theoretical guarantees and applications.

The paper develops sum-of-squares relaxations for computing $f$-divergences.

In order to model entanglements of polymers in a confined region, we consider the linking numbers and writhes of cycles in random linear embeddings of complete graphs in a cube. Our main results are that for a random linear embedding of $K_n$ in a cube, the mean sum of squared linking numbers and the mean sum of square…

New algorithm for batch list-decodable linear regression with stronger guarantees.

We consider two problems that arise in machine learning applications: the problem of recovering a planted sparse vector in a random linear subspace and the problem of decomposing a random low-rank overcomplete 3-tensor. For both problems, the best known guarantees are based on the sum-of-squares method. We develop new …

New algorithm estimates transport maps with nearly optimal error.

In this paper, we generalize the Cao-Yau's gradient estimate for the sum of squares of vector fields up to higher step under assumption of the generalized curvature-dimension inequality. With its applications, by deriving a curvature-dimension inequality, we are able to obtain the Li-Yau gradient estimate for the CR he…

Explicitly constructed 3XOR instances hard for Sum-of-Squares hierarchy.

In the noisy tensor completion problem we observe $m$ entries (whose location is chosen uniformly at random) from an unknown $n_1 \times n_2 \times n_3$ tensor $T$. We assume that $T$ is entry-wise close to being rank $r$. Our goal is to fill in its missing entries using as few observations as possible. Let $n = \max(n…

Efficiently estimates prediction error in regression with Gaussian covariates under privacy constraints.

Nearly all Gaussian points in high dimensions lie on a common ellipsoid.

Efficiently estimates covariance matrix for elliptical distributions under strong contamination.

KSOS improves kernel learning for dynamical systems via global optimization.

This note optimizes distributions using kernel mean embeddings with a new parameterization.

In this paper we prove local analytic hypoellipticity for a degenerate sum of squares of complex vector fields generalizing those of Kohn in "Hypoellipticity and Loss of Derivatives". Kohn's article is to appear in the Annals of Mathematics with an appendix by Derridj and Tartakoff proving local analyticity in that cas…

SOS programming verifies MTW tensor non-negativity for optimal transport maps.

Three algorithms improve starting solutions for clustering problems.