arXiv subjects

Ilias Zadik

Publications and source records attributed to Ilias Zadik.

At least 19 recordsLinked to original sources

arXiv2026

A Bayesian Proof of the Bernoulli Theorem

We give a new proof of the Bernoulli theorem, conjectured by Talagrand and proved in the seminal work of Bednorz and Lata{\l}a. Our approach is based on information-theoretic ideas: lower bounds on the supremum of a Bernoulli process are translated to the fundamental limits of Bayesian estimation in a Cauchy additive channel. This leads to a new information-theoretic functional that characterizes Bernoulli-process suprema and plays a role analogous to Fernique's majorizing-measure functional for Gaussian processes. The same viewpoint yields a distributional strengthening: for any prescribed law of the index, we characterize the largest expected value attainable over all couplings of that index with the Bernoulli process. This extends to Bernoulli processes a phenomenon previously understood for Gaussian processes through the work of Fernique and Talagrand.

math.PR↗

arXiv2026

Near-optimal node-private community estimation in polynomial-time

In this paper, we resolve an open question of Klopp & Zadik (2026) by providing a high-probability polynomial-time, node-private algorithm which nearly matches the performance of their exponential-time node-private algorithm for exact recovery in stochastic block models. Our result involves an explicitly constructed Lipschitz surrogate for the penalized likelihood function, as well as a carefully devised accept-reject algorithm that samples community labels from the corresponding exponential mechanism in polynomial-time. We rigorously analyze the privacy, runtime, and utility of our proposed algorithm, showing that even when the number of communities K grows logarithmically with the number of nodes n, we can achieve the minimax rates for exact recovery with the privacy parameter epsilon growing as log(n), thus matching known lower bounds on the cost of privacy for this setting.

math.ST↗

arXiv2026

A Bayesian Proof and Interpretation of Talagrand's Majorizing Measure Theorem

In this paper, we give a short Bayesian proof of Talagrand's celebrated majorizing-measure theorem (MMT). While the upper-bound direction of MMT follows relatively directly from standard arguments, the lower-bound direction is widely regarded as the more difficult part and has received several distinct proofs. Unlike previous approaches, our proof does not rely on existing Gaussian processes lower bounds techniques, nor on combinatorial, geometric, or coding-theoretic constructions. Instead, we derive the lower bound from two area identities for Gaussian additive models. We show that the Gaussian width of a finite set is the integrated mean-squared error of the maximum-likelihood estimator (MLE), while the integrated minimum mean-squared error (MMSE) is larger than the Fernique-Talagrand functional, up to a universal constant. Simply then comparing the MLE with Bayes-optimal estimation, combined with a recent duality minimax argument by Liu, gives a direct proof of the hard direction of MMT.

math.PR↗

arXiv2026

Node-Private Community Detection in Stochastic Block Models

We study community detection in stochastic block models under pure node-level differential privacy, a stringent notion that protects the participation of an individual together with all of their incident edges. This setting is substantially more challenging than edge-private community detection, since modifying a single node can affect linearly many observations. On the algorithmic side, we analyze a node-private estimator based on the exponential mechanism combined with an extension lemma, and show that exact recovery remains achievable. In the standard sparse regime with logarithmic average degree and a fixed number of communities, our results imply that a logarithmic privacy budget suffices to obtain nontrivial recovery guarantees. On the lower bound side, we show that this logarithmic scaling is in fact unavoidable: any pure node-private method must fail to achieve polynomially small exact-recovery error, or polynomially small expected mismatch, unless the privacy budget is at least of this order. Moreover, in the regime of super-logarithmic privacy budgets, our upper and lower bounds yield a matching two-term characterization of the minimax risk, with one term governed by the non-private statistical signal and the other by the privacy budget; these match up to universal constants in the exponents. Taken together, our results identify an inherent logarithmic privacy cost in node-private community detection, absent under edge differential privacy, and provide a precise rate-level characterization of the tradeoff between node privacy and SBM recovery.

math.ST↗

arXiv2026

Stable Algorithms Lower Bounds for Estimation

In this work, we show that for all statistical estimation problems, a natural MMSE instability (discontinuity) condition implies the failure of stable algorithms, serving as a version of OGP for estimation tasks. Using this criterion, we establish separations between stable and polynomial-time algorithms for the following MMSE-unstable tasks (i) Planted Shortest Path, where Dijkstra's algorithm succeeds, (ii) random Parity Codes, where Gaussian elimination succeeds, and (iii) Gaussian Subset Sum, where lattice-based methods succeed. For all three, we further show that all low-degree polynomials are stable, yielding separations against low-degree methods and a new method to bound the low-degree MMSE. In particular, our technique highlights that MMSE instability is a common feature for Shortest Path and the noiseless Parity Codes and Gaussian subset sum. Last, we highlight that our work places rigorous algorithmic footing on the long-standing physics belief that first-order phase transitions--which in this setting translates to MMSE-instability impose fundamental limits on classes of efficient algorithms.

math.ST↗

arXiv2026

The monotonicity of the Franz-Parisi potential is equivalent with Low-degree MMSE lower bounds

Over the last decades, two distinct approaches have been instrumental to our understanding of the computational complexity of statistical estimation. The statistical physics literature predicts algorithmic hardness through local stability and monotonicity properties of the Franz--Parisi (FP) potential \cite{franz1995recipes,franz1997phase}, while the mathematically rigorous literature characterizes hardness via the limitations of restricted algorithmic classes, most notably low-degree polynomial estimators \cite{hopkins2017efficient}. For many inference models, these two perspectives yield strikingly consistent predictions, giving rise to a long-standing open problem of establishing a precise mathematical relationship between them. In this work, we show that for estimation problems the power of low-degree polynomials is equivalent to the monotonicity of the annealed FP potential for a broad family of Gaussian additive models (GAMs) with signal-to-noise ratio $\lambda$. In particular, subject to a low-degree conjecture for GAMs, our results imply that the polynomial-time limits of these models are directly implied by the monotonicity of the annealed FP potential, in conceptual agreement with predictions from the physics literature dating back to the 1990s.

math.ST↗

arXiv2025

Almost-Optimal Local-Search Methods for Sparse Tensor PCA

Local-search methods are widely employed in statistical applications, yet interestingly, their theoretical foundations remain rather underexplored, compared to other classes of estimators such as low-degree polynomials and spectral methods. Of note, among the few existing results recent studies have revealed a significant "local-computational" gap in the context of a well-studied sparse tensor principal component analysis (PCA), where a broad class of local Markov chain methods exhibits a notable underperformance relative to other polynomial-time algorithms. In this work, we propose a series of local-search methods that provably "close" this gap to the best known polynomial-time procedures in multiple regimes of the model, including and going beyond the previously studied regimes in which the broad family of local Markov chain methods underperforms. Our framework includes: (1) standard greedy and randomized greedy algorithms applied to the (regularized) posterior of the model; and (2) novel random-threshold variants, in which the randomized greedy algorithm accepts a proposed transition if and only if the corresponding change in the Hamiltonian exceeds a random Gaussian threshold-rather that if and only if it is positive, as is customary. The introduction of the random thresholds enables a tight mathematical analysis of the randomized greedy algorithm's trajectory by crucially breaking the dependencies between the iterations, and could be of independent interest to the community.

math.ST↗

arXiv2025

An Optimized Franz-Parisi Criterion and its Equivalence with SQ Lower Bounds

Bandeira et al. (2022) introduced the Franz-Parisi (FP) criterion for characterizing the computational hard phases in statistical detection problems. The FP criterion, based on an annealed version of the celebrated Franz-Parisi potential from statistical physics, was shown to be equivalent to low-degree polynomial (LDP) lower bounds for Gaussian additive models, thereby connecting two distinct approaches to understanding the computational hardness in statistical inference. In this paper, we propose a refined FP criterion that aims to better capture the geometric ``overlap" structure of statistical models. Our main result establishes that this optimized FP criterion is equivalent to Statistical Query (SQ) lower bounds -- another foundational framework in computational complexity of statistical inference. Crucially, this equivalence holds under a mild, verifiable assumption satisfied by a broad class of statistical models, including Gaussian additive models, planted sparse models, as well as non-Gaussian component analysis (NGCA), single-index (SI) models, and convex truncation detection settings. For instance, in the case of convex truncation tasks, the assumption is equivalent with the Gaussian correlation inequality (Royen, 2014) from convex geometry. In addition to the above, our equivalence not only unifies and simplifies the derivation of several known SQ lower bounds -- such as for the NGCA model (Diakonikolas et al., 2017) and the SI model (Damian et al., 2024) -- but also yields new SQ lower bounds of independent interest, including for the computational gaps in mixed sparse linear regression (Arpino et al., 2023) and convex truncation (De et al., 2023).

math.ST↗

arXiv2025

The Fundamental Limits of Recovering Planted Subgraphs

Given an arbitrary subgraph $H=H_n$ and $p=p_n \in (0,1)$, the planted subgraph model is defined as follows. A statistician observes the union a random copy $H^*$ of $H$, together with random noise in the form of an instance of an Erdos-Renyi graph $G(n,p)$. Their goal is to recover the planted $H^*$ from the observed graph. Our focus in this work is to understand the minimum mean squared error (MMSE) for sufficiently large $n$. A recent paper [MNSSZ23] characterizes the graphs for which the limiting MMSE curve undergoes a sharp phase transition from $0$ to $1$ as $p$ increases, a behavior known as the all-or-nothing phenomenon, up to a mild density assumption on $H$. In this paper, we provide a formula for the limiting MMSE curve for any graph $H=H_n$, up to the same mild density assumption. This curve is expressed in terms of a variational formula over pairs of subgraphs of $H$, and is inspired by the celebrated subgraph expectation thresholds from the probabilistic combinatorics literature [KK07]. Furthermore, we give a polynomial-time description of the optimizers of this variational problem. This allows one to efficiently approximately compute the MMSE curve for any dense graph $H$ when $n$ is large enough. The proof relies on a novel graph decomposition of $H$ as well as a new minimax theorem which may be of independent interest. Our results generalize to the setting of minimax rates of recovering arbitrary monotone boolean properties planted in random noise, where the statistician observes the union of a planted minimal element $A \subseteq [N]$ of a monotone property and a random $Ber(p)^{\otimes N}$ vector. In this setting, we provide a variational formula inspired by the so-called "fractional" expectation threshold [Tal10], again describing the MMSE curve (in this case up to a multiplicative constant) for large enough $n$.

math.ST↗

arXiv2024

On The MCMC Performance In Bernoulli Group Testing And The Random Max Set-Cover Problem

The group testing problem is a canonical inference task where one seeks to identify $k$ infected individuals out of a population of $n$ people, based on the outcomes of $m$ group tests. Of particular interest is the case of Bernoulli group testing (BGT), where each individual participates in each test independently and with a fixed probability. BGT is known to be an "information-theoretically" optimal design, as there exists a decoder that can identify with high probability as $n$ grows the infected individuals using $m^*=\log_2 \binom{n}{k}$ BGT tests, which is the minimum required number of tests among \emph{all} group testing designs. An important open question in the field is if a polynomial-time decoder exists for BGT which succeeds also with $m^*$ samples. In a recent paper (Iliopoulos, Zadik COLT '21) some evidence was presented (but no proof) that a simple low-temperature MCMC method could succeed. The evidence was based on a first-moment (or "annealed") analysis of the landscape, as well as simulations that show the MCMC success for $n \approx 1000s$. In this work, we prove that, despite the intriguing success in simulations for small $n$, the class of MCMC methods proposed in previous work for BGT with $m^*$ samples takes super-polynomial-in-$n$ time to identify the infected individuals, when $k=n^{\alpha}$ for $\alpha \in (0,1)$ small enough. Towards obtaining our results, we establish the tight max-satisfiability thresholds of the random $k$-set cover problem, a result of potentially independent interest in the study of random constraint satisfaction problems.

math.ST↗

arXiv2024

On the Hardness of Learning One Hidden Layer Neural Networks

In this work, we consider the problem of learning one hidden layer ReLU neural networks with inputs from $\mathbb{R}^d$. We show that this learning problem is hard under standard cryptographic assumptions even when: (1) the size of the neural network is polynomial in $d$, (2) its input distribution is a standard Gaussian, and (3) the noise is Gaussian and polynomially small in $d$. Our hardness result is based on the hardness of the Continuous Learning with Errors (CLWE) problem, and in particular, is based on the largely believed worst-case hardness of approximately solving the shortest vector problem up to a multiplicative polynomial factor.

cs.LG↗

arXiv2024

Low-degree Security of the Planted Random Subgraph Problem

The planted random subgraph detection conjecture of Abram et al. (TCC 2023) asserts the pseudorandomness of a pair of graphs $(H, G)$, where $G$ is an Erdos-Renyi random graph on $n$ vertices, and $H$ is a random induced subgraph of $G$ on $k$ vertices. Assuming the hardness of distinguishing these two distributions (with two leaked vertices), Abram et al. construct communication-efficient, computationally secure (1) 2-party private simultaneous messages (PSM) and (2) secret sharing for forbidden graph structures. We prove the low-degree hardness of detecting planted random subgraphs all the way up to $k\leq n^{1 - \Omega(1)}$. This improves over Abram et al.'s analysis for $k \leq n^{1/2 - \Omega(1)}$. The hardness extends to $r$-uniform hypergraphs for constant $r$. Our analysis is tight in the distinguisher's degree, its advantage, and in the number of leaked vertices. Extending the constructions of Abram et al, we apply the conjecture towards (1) communication-optimal multiparty PSM protocols for random functions and (2) bit secret sharing with share size $(1 + \epsilon)\log n$ for any $\epsilon > 0$ in which arbitrary minimal coalitions of up to $r$ parties can reconstruct and secrecy holds against all unqualified subsets of up to $\ell = o(\epsilon \log n)^{1/(r-1)}$ parties.

cs.CR↗

arXiv2024

On the Low-Temperature MCMC threshold: the cases of sparse tensor PCA, sparse regression, and a geometric rule

Over the last years, there has been a significant amount of work studying the power of specific classes of computationally efficient estimators for multiple statistical parametric estimation tasks, including the estimators classes of low-degree polynomials, spectral methods, and others. Despite that, our understanding of the important class of MCMC methods remains quite poorly understood. For instance, for many models of interest, the performance of even zero-temperature (greedy-like) MCMC methods that simply maximize the posterior remains elusive. In this work, we provide an easy to check condition under which the low-temperature Metropolis chain maximizes the posterior in polynomial-time with high probability. The result is generally applicable, and in this work, we use it to derive positive MCMC results for two classical sparse estimation tasks: the sparse tensor PCA model and sparse regression. Interestingly, in both cases, we also leverage the Overlap Gap Property framework for inference (Gamarnik, Zadik AoS '22) to prove that our results are tight: no low-temperature local MCMC method can achieve better performance. In particular, our work identifies the "low-temperature (local) MCMC threshold" for both sparse models. Interestingly, in the sparse tensor PCA model our results indicate that low-temperature local MCMC methods significantly underperform compared to other studied time-efficient methods, such as the class of low-degree polynomials.

math.ST↗

arXiv2024

Counting Stars is Constant-Degree Optimal For Detecting Any Planted Subgraph

We study the computational limits of the following general hypothesis testing problem. Let H=H_n be an \emph{arbitrary} undirected graph on n vertices. We study the detection task between a ``null'' Erd\H{o}s-R\'{e}nyi random graph G(n,p) and a ``planted'' random graph which is the union of G(n,p) together with a random copy of H=H_n. Our notion of planted model is a generalization of a plethora of recently studied models initiated with the study of the planted clique model (Jerrum 1992), which corresponds to the special case where H is a k-clique and p=1/2. Over the last decade, several papers have studied the power of low-degree polynomials for limited choices of H's in the above task. In this work, we adopt a unifying perspective and characterize the power of \emph{constant degree} polynomials for the detection task, when \emph{H=H_n is any arbitrary graph} and for \emph{any p=\Omega(1).} Perhaps surprisingly, we prove that the optimal constant degree polynomial is always given by simply \emph{counting stars} in the input random graph. As a direct corollary, we conclude that the class of constant-degree polynomials is only able to ``sense'' the degree distribution of the planted graph H, and no other graph theoretic property of it.

math.ST↗

arXiv2024

Transfer Learning Beyond Bounded Density Ratios

We study the fundamental problem of transfer learning where a learning algorithm collects data from some source distribution $P$ but needs to perform well with respect to a different target distribution $Q$. A standard change of measure argument implies that transfer learning happens when the density ratio $dQ/dP$ is bounded. Yet, prior thought-provoking works by Kpotufe and Martinet (COLT, 2018) and Hanneke and Kpotufe (NeurIPS, 2019) demonstrate cases where the ratio $dQ/dP$ is unbounded, but transfer learning is possible. In this work, we focus on transfer learning over the class of low-degree polynomial estimators. Our main result is a general transfer inequality over the domain $\mathbb{R}^n$, proving that non-trivial transfer learning for low-degree polynomials is possible under very mild assumptions, going well beyond the classical assumption that $dQ/dP$ is bounded. For instance, it always applies if $Q$ is a log-concave measure and the inverse ratio $dP/dQ$ is bounded. To demonstrate the applicability of our inequality, we obtain new results in the settings of: (1) the classical truncated regression setting, where $dQ/dP$ equals infinity, and (2) the more recent out-of-distribution generalization setting for in-context learning linear functions with transformers. We also provide a discrete analogue of our transfer inequality on the Boolean Hypercube $\{-1,1\}^n$, and study its connections with the recent problem of Generalization on the Unseen of Abbe, Bengio, Lotfi and Rizk (ICML, 2023). Our main conceptual contribution is that the maximum influence of the error of the estimator $\widehat{f}-f^*$ under $Q$, $\mathrm{I}_{\max}(\widehat{f}-f^*)$, acts as a sufficient condition for transferability; when $\mathrm{I}_{\max}(\widehat{f}-f^*)$ is appropriately bounded, transfer is possible over the Boolean domain.

cs.LG↗

arXiv2023

Sharp Thresholds Imply Circuit Lower Bounds: from random 2-SAT to Planted Clique

We show that sharp thresholds for Boolean functions directly imply average-case circuit lower bounds. More formally we show that any Boolean function exhibiting a sharp enough threshold at \emph{arbitrary} critical density cannot be computed by Boolean circuits of bounded depth and polynomial size. We also prove a partial converse: if a monotone graph invariant Boolean function does not have a sharp threshold then it can be computed on average by a Boolean circuit of bounded depth and polynomial size. Our general result also implies new average-case bounded depth circuit lower bounds in a variety of settings. (a) ($k$-cliques) For $k=\Theta(n)$, we prove that any circuit of depth $d$ deciding the presence of a size $k$ clique in a random graph requires exponential-in-$n^{\Theta(1/d)}$ size. (b)(random 2-SAT) We prove that any circuit of depth $d$ deciding the satisfiability of a random 2-SAT formula requires exponential-in-$n^{\Theta(1/d)}$ size. To the best of our knowledge, this is the first bounded depth circuit lower bound for random $k$-SAT for any value of $k \geq 2.$ Our results also provide the first rigorous lower bound in agreement with a conjectured, but debated, "computational hardness" of random $k$-SAT around its satisfiability threshold. (c)(Statistical estimation -- planted $k$-clique) Over the recent years, multiple statistical estimation problems have also been proven to exhibit a "statistical" sharp threshold, called the All-or-Nothing (AoN) phenomenon. We show that AoN also implies circuit lower bounds for statistical problems. As a simple corollary of that, we prove that any circuit of depth $d$ that solves to information-theoretic optimality a "dense" variant of the celebrated planted $k$-clique problem requires exponential-in-$n^{\Theta(1/d)}$ size.

cs.CC↗

arXiv2023

Sharp thresholds in inference of planted subgraphs

A major question in the study of the Erd\H{o}s--R\'enyi random graph is to understand the probability that it contains a given subgraph. This study originated in classical work of Erd\H{o}s and R\'enyi (1960). More recent work studies this question both in building a general theory of sharp versus coarse transitions (Friedgut and Bourgain 1999; Hatami, 2012) and in results on the location of the transition (Kahn and Kalai, 2007; Talagrand, 2010; Frankston, Kahn, Narayanan, Park, 2019; Park and Pham, 2022). In inference problems, one often studies the optimal accuracy of inference as a function of the amount of noise. In a variety of sparse recovery problems, an ``all-or-nothing (AoN) phenomenon'' has been observed: Informally, as the amount of noise is gradually increased, at some critical threshold the inference problem undergoes a sharp jump from near-perfect recovery to near-zero accuracy (Gamarnik and Zadik, 2017; Reeves, Xu, Zadik, 2021). We can regard AoN as the natural inference analogue of the sharp threshold phenomenon in random graphs. In contrast with the general theory developed for sharp thresholds of random graph properties, the AoN phenomenon has only been studied so far in specific inference settings. In this paper we study the general problem of inferring a graph $H=H_n$ planted in an Erd\H{o}s--R\'enyi random graph, thus naturally connecting the two lines of research mentioned above. We show that questions of AoN are closely connected to first moment thresholds, and to a generalization of the so-called Kahn--Kalai expectation threshold that scans over subgraphs of $H$ of edge density at least $q$. In a variety of settings we characterize AoN, by showing that AoN occurs if and only if this ``generalized expectation threshold'' is roughly constant in $q$. Our proofs combine techniques from random graph theory and Bayesian inference.

math.ST↗

arXiv2022

A second moment proof of the spread lemma

This note concerns a well-known result which we term the ``spread lemma,'' which establishes the existence (with high probability) of a desired structure in a random set. The spread lemma was central to two recent celebrated results: (a) the improved bounds of Alweiss, Lovett, Wu, and Zhang (2019) on the Erd\H{o}s-Rado sunflower conjecture; and (b) the proof of the fractional Kahn--Kalai conjecture by Frankston, Kahn, Narayanan and Park (2019). While the lemma was first proved (and later refined) by delicate counting arguments, alternative proofs have also been given, via Shannon's noiseless coding theorem (Rao, 2019), and also via manipulations of Shannon entropy bounds (Tao, 2020). In this note we present a new proof of the spread lemma, that takes advantage of an explicit recasting of the proof in the language of Bayesian statistical inference. We show that from this viewpoint the proof proceeds in a straightforward and principled probabilistic manner, leading to a truncated second moment calculation which concludes the proof. The proof can also be viewed as a demonstration of the ``planting trick'' introduced by Achlioptas and Coga-Oghlan (2008) in the study of random constraint satisfaction problems.

math.CO↗