arXiv subjects

Ahmed El Alaoui

Publications and source records attributed to Ahmed El Alaoui.

34 records · Page 2Linked to original sources

arXiv2020

Algorithmic Thresholds in Mean Field Spin Glasses

Optimizing a high-dimensional non-convex function is, in general, computationally hard and many problems of this type are hard to solve even approximately. Complexity theory characterizes the optimal approximation ratios achievable in polynomial time in the worst case. On the other hand, when the objective function is random, worst case approximation ratios are overly pessimistic. Mean field spin glasses are canonical families of random energy functions over the discrete hypercube $\{-1,+1\}^N$. The near-optima of these energy landscapes are organized according to an ultrametric tree-like structure, which enjoys a high degree of universality. Recently, a precise connection has begun to emerge between this ultrametric structure and the optimal approximation ratio achievable in polynomial time in the typical case. A new approximate message passing (AMP) algorithm has been proposed that leverages this connection. The asymptotic behavior of this algorithm has been analyzed, conditional on the nature of the solution of a certain variational problem. In this paper we describe the first implementation of this algorithm and the first numerical solution of the associated variational problem. We test our approach on two prototypical mean-field spin glasses: the Sherrington-Kirkpatrick (SK) model, and the $3$-spin Ising spin glass. We observe that the algorithm works well already at moderate sizes ($N\gtrsim 1000$) and its behavior is consistent with theoretical expectations. For the SK model it asymptotically achieves arbitrarily good approximations of the global optimum. For the $3$-spin model, it achieves a constant approximation ratio that is predicted by the theory, and it appears to beat the `threshold energy' achieved by Glauber dynamics. Finally, we observe numerically that the intermediate states generated by the algorithm have the properties of ancestor states in the ultrametric tree.

cond-mat.stat-mech↗

arXiv2020

Tight Query Complexity Lower Bounds for PCA via Finite Sample Deformed Wigner Law

We prove a \emph{query complexity} lower bound for approximating the top $r$ dimensional eigenspace of a matrix. We consider an oracle model where, given a symmetric matrix $\mathbf{M} \in \mathbb{R}^{d \times d}$, an algorithm $\mathsf{Alg}$ is allowed to make $\mathsf{T}$ exact queries of the form $\mathsf{w}^{(i)} = \mathbf{M} \mathsf{v}^{(i)}$ for $i$ in $\{1,...,\mathsf{T}\}$, where $\mathsf{v}^{(i)}$ is drawn from a distribution which depends arbitrarily on the past queries and measurements $\{\mathsf{v}^{(j)},\mathsf{w}^{(i)}\}_{1 \le j \le i-1}$. We show that for every $\mathtt{gap} \in (0,1/2]$, there exists a distribution over matrices $\mathbf{M}$ for which 1) $\mathrm{gap}_r(\mathbf{M}) = Ω(\mathtt{gap})$ (where $\mathrm{gap}_r(\mathbf{M})$ is the normalized gap between the $r$ and $r+1$-st largest-magnitude eigenvector of $\mathbf{M}$), and 2) any algorithm $\mathsf{Alg}$ which takes fewer than $\mathrm{const} \times \frac{r \log d}{\sqrt{\mathtt{gap}}}$ queries fails (with overwhelming probability) to identity a matrix $\widehat{\mathsf{V}} \in \mathbb{R}^{d \times r}$ with orthonormal columns for which $\langle \widehat{\mathsf{V}}, \mathbf{M} \widehat{\mathsf{V}}\rangle \ge (1 - \mathrm{const} \times \mathtt{gap})\sum_{i=1}^r λ_i(\mathbf{M})$. Our bound requires only that $d$ is a small polynomial in $1/\mathtt{gap}$ and $r$, and matches the upper bounds of Musco and Musco '15. Moreover, it establishes a strict separation between convex optimization and \emph{randomized}, "strict-saddle" non-convex optimization of which PCA is a canonical example: in the former, first-order methods can have dimension-free iteration complexity, whereas in PCA, the iteration complexity of gradient-based methods must necessarily grow with the dimension.

cs.LG↗

arXiv2020

Imputation for High-Dimensional Linear Regression

We study high-dimensional regression with missing entries in the covariates. A common strategy in practice is to \emph{impute} the missing entries with an appropriate substitute and then implement a standard statistical procedure acting as if the covariates were fully observed. Recent literature on this subject proposes instead to design a specific, often complicated or non-convex, algorithm tailored to the case of missing covariates. We investigate a simpler approach where we fill-in the missing entries with their conditional mean given the observed covariates. We show that this imputation scheme coupled with standard off-the-shelf procedures such as the LASSO and square-root LASSO retains the minimax estimation rate in the random-design setting where the covariates are i.i.d.\ sub-Gaussian. We further show that the square-root LASSO remains \emph{pivotal} in this setting. It is often the case that the conditional expectation cannot be computed exactly and must be approximated from data. We study two cases where the covariates either follow an autoregressive (AR) process, or are jointly Gaussian with sparse precision matrix. We propose tractable estimators for the conditional expectation and then perform linear regression via LASSO, and show similar estimation rates in both cases. We complement our theoretical results with simulations on synthetic and semi-synthetic examples, illustrating not only the sharpness of our bounds, but also the broader utility of this strategy beyond our theoretical assumptions.

math.ST↗

arXiv2020

Optimization of Mean-field Spin Glasses

Mean-field spin glasses are families of random energy functions (Hamiltonians) on high-dimensional product spaces. In this paper we consider the case of Ising mixed $p$-spin models, namely Hamiltonians $H_N:Σ_N\to {\mathbb R}$ on the Hamming hypercube $Σ_N = \{\pm 1\}^N$, which are defined by the property that $\{H_N({\boldsymbol σ})\}_{{\boldsymbol σ}\in Σ_N}$ is a centered Gaussian process with covariance ${\mathbb E}\{H_N({\boldsymbol σ}_1)H_N({\boldsymbol σ}_2)\}$ depending only on the scalar product $\langle {\boldsymbol σ}_1,{\boldsymbol σ}_2\rangle$. The asymptotic value of the optimum $\max_{{\boldsymbol σ}\in Σ_N}H_N({\boldsymbol σ})$ was characterized in terms of a variational principle known as the Parisi formula, first proved by Talagrand and, in a more general setting, by Panchenko. The structure of superlevel sets is extremely rich and has been studied by a number of authors. Here we ask whether a near optimal configuration ${\boldsymbol σ}$ can be computed in polynomial time. We develop a message passing algorithm whose complexity per-iteration is of the same order as the complexity of evaluating the gradient of $H_N$, and characterize the typical energy value it achieves. When the $p$-spin model $H_N$ satisfies a certain no-overlap gap assumption, for any $\varepsilon>0$, the algorithm outputs ${\boldsymbol σ}\inΣ_N$ such that $H_N({\boldsymbol σ})\ge (1-\varepsilon)\max_{{\boldsymbol σ}'} H_N({\boldsymbol σ}')$, with high probability. The number of iterations is bounded in $N$ and depends uniquely on $\varepsilon$. More generally, regardless of whether the no-overlap gap assumption holds, the energy achieved is given by an extended variational principle, which generalizes the Parisi formula.

math.PR↗

arXiv2019

On the computational tractability of statistical estimation on amenable graphs

We consider the problem of estimating a vector of discrete variables $(θ_1,\cdots,θ_n)$, 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. Moreover, this gap is generally believed to be 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 amenable graphs (including, for instance, $d$-dimensional grids). We consider a model in which an arbitrarily small fraction of the vertex labels is revealed, and show that a linear-time local 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 still persists even when a small amount of side information is revealed.

math.PR↗

arXiv2018

Fundamental limits of detection in the spiked Wigner model

We study the fundamental limits of detecting the presence of an additive rank-one perturbation, or spike, to a Wigner matrix. When the spike comes from a prior that is i.i.d. across coordinates, we prove that the log-likelihood ratio of the spiked model against the non-spiked one is asymptotically normal below a certain reconstruction threshold which is not necessarily of a "spectral" nature, and that it is degenerate above. This establishes the maximal region of contiguity between the planted and null models. It is known that this threshold also marks a phase transition for estimating the spike: the latter task is possible above the threshold and impossible below. Therefore, both estimation and detection undergo the same transition in this random matrix model. We also provide further information about the performance of the optimal test. Our proofs are based on Gaussian interpolation methods and a rigorous incarnation of the cavity method, as devised by Guerra and Talagrand in their study of the Sherrington--Kirkpatrick spin-glass model.

math.PR↗

arXiv2018

Detection limits in the high-dimensional spiked rectangular model

We study the problem of detecting the presence of a single unknown spike in a rectangular data matrix, in a high-dimensional regime where the spike has fixed strength and the aspect ratio of the matrix converges to a finite limit. This setup includes Johnstone's spiked covariance model. We analyze the likelihood ratio of the spiked model against an "all noise" null model of reference, and show it has asymptotically Gaussian fluctuations in a region below---but in general not up to---the so-called BBP threshold from random matrix theory. Our result parallels earlier findings of Onatski et al.\ (2013) and Johnstone-Onatski (2015) for spherical spikes. We present a probabilistic approach capable of treating generic product priors. In particular, sparsity in the spike is allowed. Our approach is based on Talagrand's interpretation of the cavity method from spin-glass theory. The question of the maximal parameter region where asymptotic normality is expected to hold is left open. This region is shaped by the prior in a non-trivial way. We conjecture that this is the entire paramagnetic phase of an associated spin-glass model, and is defined by the vanishing of the replica-symmetric solution of Lesieur et al.\ (2015).

math.ST↗

arXiv2018

Estimation in the spiked Wigner model: A short proof of the replica formula

We consider the problem of estimating a rank-one perturbation of a Wigner matrix in a setting of low signal-to-noise ratio. This serves as a simple model for principal component analysis in high dimensions. The mutual information per variable between the spike and the observed matrix, or equivalently, the normalized Kullback-Leibler divergence between the planted and null models are known to converge to the so-called {\em replica-symmetric} formula, the properties of which determine the fundamental limits of estimation in this model. We provide in this note a short and transparent proof of this formula, based on simple executions of Gaussian interpolations and standard concentration-of-measure arguments. The \emph{Franz-Parisi potential}, that is, the free entropy at a fixed overlap, plays an important role in our proof. Furthermore, our proof can be generalized straightforwardly to spiked tensor models of even order.

cs.IT↗

arXiv2017

Finite Size Corrections and Likelihood Ratio Fluctuations in the Spiked Wigner Model

In this paper we study principal components analysis in the regime of high dimensionality and high noise. Our model of the problem is a rank-one deformation of a Wigner matrix where the signal-to-noise ratio (SNR) is of constant order, and we are interested in the fundamental limits of detection of the spike. Our main goal is to gain a fine understanding of the asymptotics for the log-likelihood ratio process, also known as the free energy, as a function of the SNR. Our main results are twofold. We first prove that the free energy has a finite-size correction to its limit---the replica-symmetric formula---which we explicitly compute. This provides a formula for the Kullback-Leibler divergence between the planted and null models. Second, we prove that below the reconstruction threshold, where it becomes impossible to reconstruct the spike, the log-likelihood ratio has fluctuations of constant order and converges in distribution to a Gaussian under both the planted and (under restrictions) the null model. As a consequence, we provide a general proof of contiguity between these two distributions that holds up to the reconstruction threshold, and is valid for an arbitrary separable prior on the spike. Formulae for the total variation distance, and the Type-I and Type-II errors of the optimal test are also given. Our proofs are based on Gaussian interpolation methods and a rigorous incarnation of the cavity method, as devised by Guerra and Talagrand in their study of the Sherrington--Kirkpatrick spin-glass model.

math.ST↗

arXiv2017

On the Gap Between Strict-Saddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation

We prove a \emph{query complexity} lower bound on rank-one principal component analysis (PCA). We consider an oracle model where, given a symmetric matrix $M \in \mathbb{R}^{d \times d}$, an algorithm is allowed to make $T$ \emph{exact} queries of the form $w^{(i)} = Mv^{(i)}$ for $i \in \{1,\dots,T\}$, where $v^{(i)}$ is drawn from a distribution which depends arbitrarily on the past queries and measurements $\{v^{(j)},w^{(j)}\}_{1 \le j \le i-1}$. We show that for a small constant $ε$, any adaptive, randomized algorithm which can find a unit vector $\widehat{v}$ for which $\widehat{v}^{\top}M\widehat{v} \ge (1-ε)\|M\|$, with even small probability, must make $T = Ω(\log d)$ queries. In addition to settling a widely-held folk conjecture, this bound demonstrates a fundamental gap between convex optimization and "strict-saddle" non-convex optimization of which PCA is a canonical example: in the former, first-order methods can have dimension-free iteration complexity, whereas in PCA, the iteration complexity of gradient-based methods must necessarily grow with the dimension. Our argument proceeds via a reduction to estimating the rank-one spike in a deformed Wigner model. We establish lower bounds for this model by developing a "truncated" analogue of the $χ^2$ Bayes-risk lower bound of Chen et al.

cs.LG↗

arXiv2017

Decoding from Pooled Data: Phase Transitions of Message Passing

We consider the problem of decoding a discrete signal of categorical variables from the observation of several histograms of pooled subsets of it. We present an Approximate Message Passing (AMP) algorithm for recovering the signal in the random dense setting where each observed histogram involves a random subset of entries of size proportional to n. We characterize the performance of the algorithm in the asymptotic regime where the number of observations $m$ tends to infinity proportionally to n, by deriving the corresponding State Evolution (SE) equations and studying their dynamics. We initiate the analysis of the multi-dimensional SE dynamics by proving their convergence to a fixed point, along with some further properties of the iterates. The analysis reveals sharp phase transition phenomena where the behavior of AMP changes from exact recovery to weak correlation with the signal as m/n crosses a threshold. We derive formulae for the threshold in some special cases and show that they accurately match experimental behavior.

cs.IT↗

arXiv2016

Decoding from Pooled Data: Sharp Information-Theoretic Bounds

Consider a population consisting of n individuals, each of whom has one of d types (e.g. their blood type, in which case d=4). We are allowed to query this database by specifying a subset of the population, and in response we observe a noiseless histogram (a d-dimensional vector of counts) of types of the pooled individuals. This measurement model arises in practical situations such as pooling of genetic data and may also be motivated by privacy considerations. We are interested in the number of queries one needs to unambiguously determine the type of each individual. In this paper, we study this information-theoretic question under the random, dense setting where in each query, a random subset of individuals of size proportional to n is chosen. This makes the problem a particular example of a random constraint satisfaction problem (CSP) with a "planted" solution. We establish almost matching upper and lower bounds on the minimum number of queries m such that there is no solution other than the planted one with probability tending to 1 as n tends to infinity. Our proof relies on the computation of the exact "annealed free energy" of this model in the thermodynamic limit, which corresponds to the exponential rate of decay of the expected number of solution to this planted CSP. As a by-product of the analysis, we show an identity of independent interest relating the Gaussian integral over the space of Eulerian flows of a graph to its spanning tree polynomial.

math.PR↗

arXiv2016

Asymptotic behavior of $\ell_p$-based Laplacian regularization in semi-supervised learning

Given a weighted graph with $N$ vertices, consider a real-valued regression problem in a semi-supervised setting, where one observes $n$ labeled vertices, and the task is to label the remaining ones. We present a theoretical study of $\ell_p$-based Laplacian regularization under a $d$-dimensional geometric random graph model. We provide a variational characterization of the performance of this regularized learner as $N$ grows to infinity while $n$ stays constant, the associated optimality conditions lead to a partial differential equation that must be satisfied by the associated function estimate $\hat{f}$. From this formulation we derive several predictions on the limiting behavior the $d$-dimensional function $\hat{f}$, including (a) a phase transition in its smoothness at the threshold $p = d + 1$, and (b) a tradeoff between smoothness and sensitivity to the underlying unlabeled data distribution $P$. Thus, over the range $p \leq d$, the function estimate $\hat{f}$ is degenerate and "spiky," whereas for $p\geq d+1$, the function estimate $\hat{f}$ is smooth. We show that the effect of the underlying density vanishes monotonically with $p$, such that in the limit $p = \infty$, corresponding to the so-called Absolutely Minimal Lipschitz Extension, the estimate $\hat{f}$ is independent of the distribution $P$. Under the assumption of semi-supervised smoothness, ignoring $P$ can lead to poor statistical performance, in particular, we construct a specific example for $d=1$ to demonstrate that $p=2$ has lower risk than $p=\infty$ due to the former penalty adapting to $P$ and the latter ignoring it. We also provide simulations that verify the accuracy of our predictions for finite sample sizes. Together, these properties show that $p = d+1$ is an optimal choice, yielding a function estimate $\hat{f}$ that is both smooth and non-degenerate, while remaining maximally sensitive to $P$.

cs.LG↗

arXiv2015

Fast Randomized Kernel Methods With Statistical Guarantees

One approach to improving the running time of kernel-based machine learning methods is to build a small sketch of the input and use it in lieu of the full kernel matrix in the machine learning task of interest. Here, we describe a version of this approach that comes with running time guarantees as well as improved guarantees on its statistical performance. By extending the notion of \emph{statistical leverage scores} to the setting of kernel ridge regression, our main statistical result is to identify an importance sampling distribution that reduces the size of the sketch (i.e., the required number of columns to be sampled) to the \emph{effective dimensionality} of the problem. This quantity is often much smaller than previous bounds that depend on the \emph{maximal degrees of freedom}. Our main algorithmic result is to present a fast algorithm to compute approximations to these scores. This algorithm runs in time that is linear in the number of samples---more precisely, the running time is $O(np^2)$, where the parameter $p$ depends only on the trace of the kernel matrix and the regularization parameter---and it can be applied to the matrix of feature vectors, without having to form the full kernel matrix. This is obtained via a variant of length-squared sampling that we adapt to the kernel setting in a way that is of independent interest. Lastly, we provide empirical results illustrating our theory, and we discuss how this new notion of the statistical leverage of a data point captures in a fine way the difficulty of the original statistical learning problem.

stat.ML↗

arXiv2014

Computing the log-determinant of symmetric, diagonally dominant matrices in near-linear time

We present new algorithms for computing the log-determinant of symmetric, diagonally dominant matrices. Existing algorithms run with cubic complexity with respect to the size of the matrix in the worst case. Our algorithm computes an approximation of the log-determinant in time near-linear with respect to the number of non-zero entries and with high probability. This algorithm builds upon the utra-sparsifiers introduced by Spielman and Teng for Laplacian matrices and ultimately uses their refined versions introduced by Koutis, Miller and Peng in the context of solving linear systems. We also present simpler algorithms that compute upper and lower bounds and that may be of more immediate practical interest.

math.NA↗

arXiv2012

Measurement of the generalized form factors near threshold via $γ^* p \to nπ^+$ at high $Q^2$

We report the first extraction of the pion-nucleon multipoles near the production threshold for the $nπ^+$ channel at relatively high momentum transfer ($Q^2$ up to 4.2 $\rm{GeV^2}$). The dominance of the s-wave transverse multipole ($E_{0+}$), expected in this region, allowed us to access the generalized form factor $G_1$ within the light-cone sum rule (LCSR) framework as well as the axial form factor $G_A$. The data analyzed in this work were collected by the nearly $4π$ CEBAF Large Acceptance Spectrometer (CLAS) using a 5.754 $\rm{GeV}$ electron beam on a proton target. The differential cross section and the $π-N$-multipole $E_{0+}/G_D$ were measured using two different methods, the LCSR and a direct multipole fit. The results from the two methods are found to be consistent and almost $Q^2$ independent.

nucl-ex↗