arXiv subjects

Ahmed El Alaoui

Publications and source records attributed to Ahmed El Alaoui.

At least 19 recordsLinked to original sources

arXiv2026

Free-Probabilistic State Evolution and Random Matrix Discrepancy

Let $A_1,\ldots,A_n$ be independent $d \times d$ real symmetric Gaussian random matrices, and consider the linear operator $A(x) = n^{-1/2}\sum_{i=1}^n x_i A_i$, $x\in \mathbb{R}^n$. We construct an iterative algorithm in the Approximate Message Passing family which iterates over $A$ and its adjoint $A^*$, and establish a state evolution result which characterizes its behavior in the limit $d\rightarrow \infty, 2n/d^2 \rightarrow α$ in terms of a correlated Gaussian-semicircular process in a free probability space, in the sense of strong convergence of operators. We then apply this iteration to the random matrix discrepancy problem which asks for a binary vector $x \in \{-1,+1\}^n$ such that $A(x)$ has a small operator norm. Our algorithm achieves an operator norm $2σ(α)$, for an explicit expression of the standard deviation $σ(α)<1$ for all $0<α<α_* \simeq 5.74$. This resolves the algorithmic question of Kunisky-Zhang (2023) and Maillard (2025) in this interval.

math.PR↗

arXiv2026

Mixing of Glauber Dynamics on High Overlap Gibbs Measures

We show fast mixing of Glauber dynamics for certain quadratic Gibbs measures with large external fields. The main ingredient is an overlap condition that allows us to control correlation matrices uniformly over all pinnings, by controlling norms of small submatrices of the interaction matrix. Using stochastic localization, we then obtain a lower bound on the spectral gap and, consequently, polynomial-time mixing of Glauber dynamics. As a direct application, we consider the Sherrington-Kirkpatrick model, whose interaction matrix is a scaled GOE matrix. For this model, we show that for any fixed finite inverse temperature $β$, there exists a strength of external field $θ$, not depending on the size of the system, for which Glauber dynamics mixes in polynomial time (with high probability on the draw of the interaction matrix).

math.PR↗

arXiv2026

How abundant are good interpolators?

Let $S$ be the set of unit norm linear classifiers $θ\in \mathbb{R}^d$ which correctly classify every point of a labeled dataset $(X_i,y_i)_{i=1}^n$, $X_i \in \mathbb{R}^d$, $y_i \in \{-1,+1\}$, with a possibly negative margin $κ$ fixed in advance. Under two natural data-generating distributions of the $(X,y)$ pairs -- a Gaussian mixture model and a logistic model with Gaussian features -- and in the proportional regime $n/d \to α$ with small enough $α$, we establish a large deviation principle on the event that a point $θ$ chosen uniformly at random from $S$ achieves a given generalization error, with high probability over the choice of the data. The associated large deviation rate function is deterministic and describes the proportion, at the exponential scale in $d$, of interpolating classifiers having a given desired performance. As a consequence, we establish the following concentration phenomenon: all but an exponentially small fraction of interpolating classifiers have approximately the same generalization performance given by the unique maximizer of this rate function. We numerically compare this maximizer to the performance of empirical risk minimization by gradient descent and to the performance of a natural linear program, both finding a point in $S$, and deduce that in the overparametrized regime of small $α$, these efficient procedures outperform the vast majority of interpolators, pointing to their nontrivial benign overfitting in this setting.

math.ST↗

arXiv2025

The Kikuchi Hierarchy and Tensor PCA

For the tensor PCA (principal component analysis) problem, we propose a new hierarchy of increasingly powerful algorithms with increasing runtime. Our hierarchy is analogous to the sum-of-squares (SOS) hierarchy but is instead inspired by statistical physics and related algorithms such as belief propagation and AMP (approximate message passing). Our level-$\ell$ algorithm can be thought of as a linearized message-passing algorithm that keeps track of $\ell$-wise dependencies among the hidden variables. Specifically, our algorithms are spectral methods based on the Kikuchi Hessian, which generalizes the well-studied Bethe Hessian to the higher-order Kikuchi free energies. It is known that AMP, the flagship algorithm of statistical physics, has substantially worse performance than SOS for tensor PCA. In this work we 'redeem' the statistical physics approach by showing that our hierarchy gives a polynomial-time algorithm matching the performance of SOS. Our hierarchy also yields a continuum of subexponential-time algorithms, and we prove that these achieve the same (conjecturally optimal) tradeoff between runtime and statistical power as SOS. Our proofs are much simpler than prior work, and also apply to the related problem of refuting random $k$-XOR formulas. The results we present here apply to tensor PCA for tensors of all orders, and to $k$-XOR when $k$ is even. Our methods suggest a new avenue for systematically obtaining optimal algorithms for Bayesian inference problems, and our results constitute a step toward unifying the statistical physics and sum-of-squares approaches to algorithm design.

cs.DS↗

arXiv2025

Hardness of sampling solutions from the Symmetric Binary Perceptron

We show that two related classes of algorithms, stable algorithms and Boolean circuits with bounded depth, cannot produce an approximate sample from the uniform measure over the set of solutions to the symmetric binary perceptron model at any constraint-to-variable density. This result is in contrast to the question of finding \emph{a} solution to the same problem, where efficient (and stable) algorithms are known to succeed at sufficiently low density. This result suggests that the solutions found efficiently -- whenever this task is possible -- must be highly atypical, and therefore provides an example of a problem where search is efficiently possible but approximate sampling from the set of solutions is not, at least within these two classes of algorithms.

math.PR↗

arXiv2025

On the Discontinuous Breaking of Replica Symmetry and Shattering in Mean-Field Spin Glasses

We show that in mean-field spin glasses, a discontinuous breaking of replica symmetry at the critical inverse temperature $β_c$ implies the existence of an intermediate shattered phase. This confirms a prediction from physics regarding the nature of random first order phase transitions. On the other hand, we give an example of a spherical spin glass which exhibits shattering, yet the transition is continuous at $β_c$.

math.PR↗

arXiv2025

Shattering in Pure Spherical Spin Glasses

We prove the existence of a shattered phase within the replica-symmetric phase of the pure spherical $p$-spin models for $p$ sufficiently large. In this phase, we construct a decomposition of the sphere into well-separated small clusters, each of which has exponentially small Gibbs mass, yet which together carry all but an exponentially small fraction of the Gibbs mass. We achieve this via quantitative estimates on the derivative of the Franz--Parisi potential, which measures the Gibbs mass profile around a typical sample. Corollaries on dynamics are derived, in particular we show the two-times correlation function of stationary Langevin dynamics must have an exponentially long plateau. We further show that shattering implies disorder chaos for the Gibbs measure in the optimal transport sense; this is known to imply failure of sampling algorithms which are stable under perturbation in the same metric.

math.PR↗

arXiv2025

Near-optimal shattering in the Ising pure p-spin and rarity of solutions returned by stable algorithms

We show that in the Ising pure $p$-spin model of spin glasses, shattering takes place at all inverse temperatures $β\in (\sqrt{(2 \log p)/p}, \sqrt{2\log 2})$ when $p$ is sufficiently large as a function of $β$. Of special interest is the lower boundary of this interval which matches the large $p$ asymptotics of the inverse temperature marking the hypothetical dynamical transition predicted in statistical physics. We show this as a consequence of a `soft' version of the overlap gap property which asserts the existence of a distance gap of points of typical energy from a typical sample from the Gibbs measure. We further show that this latter property implies that stable algorithms seeking to return a point of at least typical energy are confined to an exponentially rare subset of that super-level set, provided that their success probability is not vanishingly small.

math.PR↗

arXiv2024

Bounds on the covariance matrix of the Sherrington-Kirkpatrick model

We consider the Sherrington-Kirkpatrick model with no external field and inverse temperature $β<1$ and prove that the expected operator norm of the covariance matrix of the Gibbs measure is bounded by a constant depending only on $β$. This answers an open question raised by Talagrand, who proved a bound of $C(β) (\log n)^8$. Our result follows by establishing an approximate formula for the covariance matrix which we obtain by differentiating the TAP equations and then optimally controlling the associated error terms. We complement this result by showing diverging lower bounds on the operator norm, both at the critical and low temperatures.

math.PR↗

arXiv2024

Fast relaxation of the random field Ising dynamics

We study the convergence properties of Glauber dynamics for the random field Ising model (RFIM) with ferromagnetic interactions on finite domains of $\mathbb{Z}^d$, $d \ge 2$. Of particular interest is the Griffiths phase where correlations decay exponentially fast in expectation over the quenched disorder, but there exist arbitrarily large islands of weak fields where low-temperature behavior is observed. Our results are twofold: 1. Under weak spatial mixing (boundary-to-bulk exponential decay of correlations) in expectation, we show that the dynamics satisfy a weak Poincaré inequality implying algebraic relaxation to equilibrium over timescales polynomial in the volume $N$ of the domain, and polynomial time mixing from a warm start. From this we construct a polynomial-time approximate sampling algorithm based on running Glauber dynamics over an increasing sequence of approximations of the domain. 2. Under strong spatial mixing (exponential decay of correlations even near boundary pinnings) in expectation, we prove a full Poincaré inequality, implying exponential relaxation to equilibrium and $N^{o(1)}$-mixing time. Note by way of example, both weak and strong spatial mixing hold at any temperature, provided the external fields are strong enough. Our proofs combine a stochastic localization technique which has the effect of increasing the variance of the field, with a field-dependent coarse graining which controls the resulting sub-critical percolation process of sites with weak fields.

math.PR↗

arXiv2024

On the Atypical Solutions of the Symmetric Binary Perceptron

We study the random binary symmetric perceptron problem, focusing on the behavior of rare high-margin solutions. While most solutions are isolated, we demonstrate that these rare solutions are part of clusters of extensive entropy, heuristically corresponding to non-trivial fixed points of an approximate message-passing algorithm. We enumerate these clusters via a local entropy, defined as a Franz-Parisi potential, which we rigorously evaluate using the first and second moment methods in the limit of a small constraint density $α$ (corresponding to vanishing margin $κ$) under a certain assumption on the concentration of the entropy. This examination unveils several intriguing phenomena: i) We demonstrate that these clusters have an entropic barrier in the sense that the entropy as a function of the distance from the reference high-margin solution is non-monotone when $κ\le 1.429 \sqrt{-α/\logα}$, while it is monotone otherwise, and that they have an energetic barrier in the sense that there are no solutions at an intermediate distance from the reference solution when $κ\le 1.239 \sqrt{-α/ \logα}$. The critical scaling of the margin $κ$ in $\sqrt{-α/\logα}$ corresponds to the one obtained from the earlier work of Gamarnik et al. (2022) for the overlap-gap property, a phenomenon known to present a barrier to certain efficient algorithms. ii) We establish using the replica method that the complexity (the logarithm of the number of clusters of such solutions) versus entropy (the logarithm of the number of solutions in the clusters) curves are partly non-concave and correspond to very large values of the Parisi parameter, with the equilibrium being reached when the Parisi parameter diverges.

math.PR↗

arXiv2024

Sampling from the Sherrington-Kirkpatrick Gibbs measure via algorithmic stochastic localization

We consider the Sherrington-Kirkpatrick model of spin glasses at high-temperature and no external field, and study the problem of sampling from the Gibbs distribution $μ$ in polynomial time. We prove that, for any inverse temperature $β<1/2$, there exists an algorithm with complexity $O(n^2)$ that samples from a distribution $μ^{alg}$ which is close in normalized Wasserstein distance to $μ$. Namely, there exists a coupling of $μ$ and $μ^{alg}$ such that if $(x,x^{alg})\in\{-1,+1\}^n\times \{-1,+1\}^n$ is a pair drawn from this coupling, then $n^{-1}\mathbb E\{||x-x^{alg}||_2^2\}=o_n(1)$. The best previous results, by Bauerschmidt and Bodineau and by Eldan, Koehler, and Zeitouni, implied efficient algorithms to approximately sample (under a stronger metric) for $β<1/4$. We complement this result with a negative one, by introducing a suitable "stability" property for sampling algorithms, which is verified by many standard techniques. We prove that no stable algorithm can approximately sample for $β>1$, even under the normalized Wasserstein metric. Our sampling method is based on an algorithmic implementation of stochastic localization, which progressively tilts the measure $μ$ towards a single configuration, together with an approximate message passing algorithm that is used to approximate the mean of the tilted measure.

math.PR↗

arXiv2023

Sampling from Mean-Field Gibbs Measures via Diffusion Processes

We consider Ising mixed $p$-spin glasses at high-temperature and without external field, and study the problem of sampling from the Gibbs distribution $μ$ in polynomial time. We develop a new sampling algorithm with complexity of the same order as evaluating the gradient of the Hamiltonian and, in particular, at most linear in the input size. We prove that, at sufficiently high-temperature, it produces samples from a distribution $μ^{alg}$ which is close in normalized Wasserstein distance to $μ$. Namely, there exists a coupling of $μ$ and $μ^{alg}$ such that if $({\boldsymbol x},{\boldsymbol x}^{alg})\in\{-1,+1\}^n\times \{-1,+1\}^n$ is a pair drawn from this coupling, then $n^{-1}{\mathbb E}\{\|{\boldsymbol x}-{\boldsymbol x}^{alg}\|_2^2\}=o_n(1)$. For the case of the Sherrington-Kirkpatrick model, our algorithm succeeds in the full replica-symmetric phase. We complement this result with a negative one for sampling algorithms satisfying a certain `stability' property, which is verified by many standard techniques. No stable algorithm can approximately sample at temperatures below the onset of shattering, even under the normalized Wasserstein metric. Further, no algorithm can sample at temperatures below the onset of replica symmetry breaking. Our sampling method implements a discretized version of a diffusion process that has become recently popular in machine learning under the name of `denoising diffusion.' We derive the same process from the general construction of stochastic localization. Implementing the diffusion process requires to efficiently approximate the mean of the tilted measure. To this end, we use an approximate message passing algorithm that, as we prove, achieves sufficiently accurate mean estimation.

math.PR↗

arXiv2023

Local algorithms for Maximum Cut and Minimum Bisection on locally treelike regular graphs of large degree

Given a graph $G$ of degree $k$ over $n$ vertices, we consider the problem of computing a near maximum cut or a near minimum bisection in polynomial time. For graphs of girth $2L$, we develop a local message passing algorithm whose complexity is $O(nkL)$, and that achieves near optimal cut values among all $L$-local algorithms. Focusing on max-cut, the algorithm constructs a cut of value $nk/4+ n\mathsf{P}_\star\sqrt{k/4}+\mathsf{err}(n,k,L)$, where $\mathsf{P}_\star\approx 0.763166$ is the value of the Parisi formula from spin glass theory, and $\mathsf{err}(n,k,L)=o_n(n)+no_k(\sqrt{k})+n \sqrt{k} o_L(1)$ (subscripts indicate the asymptotic variables). Our result generalizes to locally treelike graphs, i.e., graphs whose girth becomes $2L$ after removing a small fraction of vertices. Earlier work established that, for random $k$-regular graphs, the typical max-cut value is $nk/4+ n\mathsf{P}_\star\sqrt{k/4}+o_n(n)+no_k(\sqrt{k})$. Therefore our algorithm is nearly optimal on such graphs. An immediate corollary of this result is that random regular graphs have nearly minimum max-cut, and nearly maximum min-bisection among all regular locally treelike graphs. This can be viewed as a combinatorial version of the near-Ramanujan property of random regular graphs.

math.PR↗

arXiv2022

The Franz-Parisi Criterion and Computational Trade-offs in High Dimensional Statistics

Many high-dimensional statistical inference problems are believed to possess inherent computational hardness. Various frameworks have been proposed to give rigorous evidence for such hardness, including lower bounds against restricted models of computation (such as low-degree functions), as well as methods rooted in statistical physics that are based on free energy landscapes. This paper aims to make a rigorous connection between the seemingly different low-degree and free-energy based approaches. We define a free-energy based criterion for hardness and formally connect it to the well-established notion of low-degree hardness for a broad class of statistical problems, namely all Gaussian additive models and certain models with a sparse planted signal. By leveraging these rigorous connections we are able to: establish that for Gaussian additive models the "algebraic" notion of low-degree hardness implies failure of "geometric" local MCMC algorithms, and provide new low-degree lower bounds for sparse linear regression which seem difficult to prove directly. These results provide both conceptual insights into the connections between different notions of hardness, as well as concrete technical tools such as new methods for proving low-degree lower bounds.

math.ST↗

arXiv2021

An Information-Theoretic View of Stochastic Localization

Given a probability measure $μ$ over ${\mathbb R}^n$, it is often useful to approximate it by the convex combination of a small number of probability measures, such that each component is close to a product measure. Recently, Ronen Eldan used a stochastic localization argument to prove a general decomposition result of this type. In Eldan's theorem, the `number of components' is characterized by the entropy of the mixture, and `closeness to product' is characterized by the covariance matrix of each component. We present an elementary proof of Eldan's theorem which makes use of an information theory (or estimation theory) interpretation. The proof is analogous to the one of an earlier decomposition result known as the `pinning lemma.'

cs.IT↗

arXiv2021

Efficient $\mathbb{Z}_2$ synchronization on $\mathbb{Z}^d$ under symmetry-preserving side information

We consider $\mathbb{Z}_2$-synchronization on the Euclidean lattice. Every vertex of $\mathbb{Z}^d$ is assigned an independent symmetric random sign $θ_u$, and for every edge $(u,v)$ of the lattice, one observes the product $θ_uθ_v$ flipped independently with probability $p$. The task is to reconstruct products $θ_uθ_v$ for pairs of vertices $u$ and $v$ which are arbitrarily far apart. Abbé, Massoulié, Montanari, Sly and Srivastava (2018) showed that synchronization is possible if and only if $p$ is below a critical threshold $\tilde{p}_c(d)$, and efficiently so for $p$ small enough. We augment this synchronization setting with a model of side information preserving the sign symmetry of $θ$, and propose an \emph{efficient} algorithm which synchronizes a randomly chosen pair of far away vertices on average, up to a differently defined critical threshold $p_c(d)$. We conjecture that $ p_c(d)=\tilde{p}_c(d)$ for all $d \ge 2$. Our strategy is to \emph{renormalize} the synchronization model in order to reduce the effective noise parameter, and then apply a variant of the multiscale algorithm of AMMSS. The success of the renormalization procedure is conditional on a plausible but unproved assumption about the regularity of the free energy of an Ising spin glass model on $\mathbb{Z}^d$.

math.PR↗

arXiv2020

Algorithmic pure states for the negative spherical perceptron

We consider the spherical perceptron with Gaussian disorder. This is the set $S$ of points $σ\in \mathbb{R}^N$ on the sphere of radius $\sqrt{N}$ satisfying $\langle g_a , σ\rangle \ge κ\sqrt{N}\,$ for all $1 \le a \le M$, where $(g_a)_{a=1}^M$ are independent standard gaussian vectors and $κ\in \mathbb{R}$ is fixed. Various characteristics of $S$ such as its surface measure and the largest $M$ for which it is non-empty, were computed heuristically in statistical physics in the asymptotic regime $N \to \infty$, $M/N \to α$. The case $κ<0$ is of special interest as $S$ is conjectured to exhibit a hierarchical tree-like geometry known as "full replica-symmetry breaking" (FRSB) close to the satisfiability threshold $α_{\text{SAT}}(κ)$, and whose characteristics are captured by a Parisi variational principle akin to the one appearing in the Sherrington-Kirkpatrick model. In this paper we design an efficient algorithm which, given oracle access to the solution of the Parisi variational principle, exploits this conjectured FRSB structure for $κ<0$ and outputs a vector $\hatσ$ satisfying $\langle g_a , \hatσ\rangle \ge κ\sqrt{N}$ for all $1\le a \le M$ and lying on a sphere of non-trivial radius $\sqrt{\bar{q} N}$, where $\bar{q} \in (0,1)$ is the right-end of the support of the associated Parisi measure. We expect $\hatσ$ to be approximately the barycenter of a pure state of the spherical perceptron. Moreover we expect that $\bar{q} \to 1$ as $α\to α_{\text{SAT}}(κ)$, so that $\big\langle g_a,\hatσ/|\hatσ|\big\rangle \geq (κ-o(1))\sqrt{N}$ near criticality.

math.PR↗