arXiv subjects

Samuel B. Hopkins

Publications and source records attributed to Samuel B. Hopkins.

At least 19 recordsLinked to original sources

arXiv2026

A Simple Algorithm for Best Separable State

We study the best separable state problem (BSS), which asks for the maximum acceptance probability of a quantum measurement over unentangled states. In classical terms, the goal is to maximize $\langle(x \otimes y), M (x \otimes y)\rangle$ over unit vectors $x,y$ where $0 \preceq M \preceq I$; we call this value $\mathrm{BSS}(M)$. We study $\mathrm{BSS}$ in the "perfect completeness" regime, where given $M$ such that $\mathrm{BSS}(M) = 1$ the goal is to find the best possible solution $x,y$ -- this generalizes the problem of finding a rank-one matrix as close as possible to a given subspace of $\mathbb{R}^{n \times n}$ guaranteed to contain a rank-one matrix. The strongest known algorithmic guarantees for this problem are: (1) an algorithm which finds a solution with value $1-\varepsilon$ in time $\exp(\sqrt{n} (\log n)^{O(1)} / \varepsilon^2)$, due to Barak, Kothari, and Steurer, and (2) an algorithm which finds a solution with value $q/n$ in time roughly $n^{O(q)}$, due to Bhattiprolu, Ghosh, Guruswami, Lee, and Tulsiani. We give a much simpler approach to rounding the SoS relaxation, generalizing the canonical "global correlation rounding" technique, and obtain a better running time. Given $M$ with $\mathrm{BSS}(M) = 1$, our algorithm finds a solution with value $1-\epsilon$ in time $n^{O(\sqrt{n/\varepsilon})}$, and a solution of value $q/n$ in time $n^{O(\sqrt q)}$. Using the same techniques, we prove a new variant of the "pinning lemma", a measure-decomposition theorem widely used in LP/SDP rounding, high-dimensional probability, and statistical physics, which we believe is of independent interest.

cs.DS↗

arXiv2026

Algorithms with Polynomially-Improved Approximation Factors for the $2 \rightarrow q$ Norm, and Applications

The $2 \rightarrow q$ norm of a matrix $X \in \mathbb{R}^{n \times d}$ is defined as $\lVert X \rVert_{2 \rightarrow q} = \sup_{\lVert v \rVert_2 = 1} \lVert Xv \rVert_q$. We give polynomial-time multiplicative approximation algorithms for this norm when $q > 2$ (i.e. in the hypercontractive setting). This problem either directly captures or is closely related to long-standing open problems in combinatorial optimization and hardness of approximation (e.g. Small Set Expansion), quantum information (e.g. Best Separable State), and algorithmic statistics. Very little is known about what approximation factors we can achieve for this problem in polynomial time, even though such approximations have significant downstream consequences. Barak, Brand\~{a}o, Harrow, Kelner, Steurer, and Zhou showed that no polynomial-time algorithm can achieve an approximation factor better than $2^{\sqrt{\log n}}$, assuming the Exponential Time Hypothesis (FOCS'12). On the other hand, a simple spectral algorithm gives a $d^{1/4}$-approximation as a baseline. For the important special case of $q = 4$, prior work of Guth, Maldague, and Urschel (SIAM Matrix Analysis and Applications'25) can be combined with known sparsification techniques to give a $d^{1/6}$-approximation. We improve over these results by polynomial factors, giving a $d^{1/8}$-approximation. Moreover, we construct sum-of-squares certificates for the $2 \rightarrow q$ norm. This directly implies improved algorithms for robust mean and covariance estimation, robust regression, and clustering, when the data only satisfies a bound on its $q$-th moment.

cs.DS↗

arXiv2026

On the Accuracy of Newton Step and Influence Function Data Attributions

Data attribution aims to explain model predictions by estimating how they would change if certain training points were removed, and is used in a wide range of applications, from interpretability and credit assignment to unlearning and privacy. Even in the relatively simple case of logistic regressions, existing mathematical analyses of leading data attribution methods such as Influence Functions (IF) and single Newton Step (NS) remain limited in two key ways. First, they rely on global strong convexity assumptions which are often not satisfied in practice. Second, the resulting bounds scale very poorly with the number of parameters ($d$) and the number of samples removed ($k$). As a result, these analyses are not tight enough to answer fundamental questions such as "what is the asymptotic scaling of the errors of each method?" or "which of these methods is more accurate for a given dataset?" In this paper, we introduce a new analysis of the NS and IF data attribution methods for convex learning problems. To the best of our knowledge, this is the first analysis of these questions that does not assume global strong convexity and also the first explanation of [KATL19] and [RH25a]'s observation that NS data attribution is often more accurate than IF. We prove that for sufficiently well-behaved logistic regressions, our bounds are asymptotically tight up to poly-logarithmic factors, yielding scaling laws for the errors in the average-case sample removals. \[ \mathbb{E}_{T \subseteq [n],\, |T| = k} \bigl[ \|\hatθ_T - \hatθ_T^{\mathrm{NS}}\|_2 \bigr] = \widetildeΘ\!\left(\frac{k d}{n^2}\right), \qquad \mathbb{E}_{T \subseteq [n],\, |T| = k} \bigl[ \|\hatθ_T^{\mathrm{NS}} - \hatθ_T^{\mathrm{IF}}\|_2 \bigr] = \widetildeΘ\!\left( \frac{(k + d)\sqrt{k d}}{n^2} \right). \]

cs.LG↗

arXiv2026

Entrywise Low-Rank Approximation and Matrix $p \rightarrow q$ Norms via Global Correlation Rounding

Given a matrix $A$, the goal of the entrywise low-rank approximation problem is to find $\operatorname{argmin} \|A-B\|_p$ over all rank-$k$ matrices $B$, where $\| \cdot \|_p$ is the entrywise $\ell_p$ norm. When $p = 2$ this well-studied problem is solved by the singular value decomposition, but for $p \neq 2$ the problem becomes computationally challenging. For every even $p > 2$ and every fixed $k$, we give the first polynomial-time approximation scheme for this problem, improving on the $(3 + \varepsilon)$ approximation of Ban, Bhattiprolu, Bringmann, Kolev, Lee, and Woodruff, the bi-criteria approximation of Woodruff and Yasuda, and the additive approximation scheme of Anderson, Bakshi, and Hopkins. Prior algorithmic approaches based on sketching and column selection, which yielded a polynomial-time approximation scheme in the $p < 2$ setting, face concrete barriers when $p > 2$. Instead, we use the Sherali-Adams hierarchy of convex programs, and in so doing establish a blueprint for how to use convex hierarchies to design polynomial-time approximation schemes for continuous optimization problems. We use the same algorithmic strategy to give a new family of additive approximation algorithms for matrix $p \rightarrow q$ norms, which are intimately related to small-set expansion and quantum information. In particular, we give the first nontrivial additive approximation algorithms in the regime $p < 2 < q$.

cs.DS↗

arXiv2025

Fast, Sample-Efficient, Affine-Invariant Private Mean and Covariance Estimation for Subgaussian Distributions

We present a fast, differentially private algorithm for high-dimensional covariance-aware mean estimation with nearly optimal sample complexity. Only exponential-time estimators were previously known to achieve this guarantee. Given $n$ samples from a (sub-)Gaussian distribution with unknown mean $μ$ and covariance $Σ$, our $(\varepsilon,δ)$-differentially private estimator produces $\tildeμ$ such that $\|μ- \tildeμ\|_Σ \leq α$ as long as $n \gtrsim \tfrac d {α^2} + \tfrac{d \sqrt{\log 1/δ}}{α\varepsilon}+\frac{d\log 1/δ}{\varepsilon}$. The Mahalanobis error metric $\|μ- \hatμ\|_Σ$ measures the distance between $\hat μ$ and $μ$ relative to $Σ$; it characterizes the error of the sample mean. Our algorithm runs in time $\tilde{O}(nd^{ω- 1} + nd/\varepsilon)$, where $ω< 2.38$ is the matrix multiplication exponent. We adapt an exponential-time approach of Brown, Gaboardi, Smith, Ullman, and Zakynthinou (2021), giving efficient variants of stable mean and covariance estimation subroutines that also improve the sample complexity to the nearly optimal bound above. Our stable covariance estimator can be turned to private covariance estimation for unrestricted subgaussian distributions. With $n\gtrsim d^{3/2}$ samples, our estimate is accurate in spectral norm. This is the first such algorithm using $n= o(d^2)$ samples, answering an open question posed by Alabi et al. (2022). With $n\gtrsim d^2$ samples, our estimate is accurate in Frobenius norm. This leads to a fast, nearly optimal algorithm for private learning of unrestricted Gaussian distributions in TV distance. Duchi, Haque, and Kuditipudi (2023) obtained similar results independently and concurrently.

cs.LG↗

arXiv2025

Faster MAX-CUT on Bounded Threshold Rank Graphs

We design new algorithms for approximating 2CSPs on graphs with bounded threshold rank, that is, whose normalized adjacency matrix has few eigenvalues larger than $\varepsilon$, smaller than $-\varepsilon$, or both. Unlike on worst-case graphs, 2CSPs on bounded threshold rank graphs can be $(1+O(\varepsilon))$-approximated efficiently. Prior approximation algorithms for this problem run in time exponential in the threshold rank and $1/\varepsilon$. Our algorithm has running time which is polynomial in $1/\varepsilon$ and exponential in the threshold rank of the label-extended graph, and near-linear in the input size. As a consequence, we obtain the first $(1+O(\varepsilon))$ approximation for MAX-CUT on bounded threshold rank graphs running in $\mathrm{poly}(1/\varepsilon)$ time. We also improve the state-of-the-art running time for 2CSPs on bounded threshold-rank graphs from polynomial in input size to near-linear via a new comparison inequality between the threshold rank of the label-extended graph and base graph. Our algorithm is a simple yet novel combination of subspace enumeration and semidefinite programming.

cs.DS↗

arXiv2025

Additive Approximation Schemes for Low-Dimensional Embeddings

We consider the task of fitting low-dimensional embeddings to high-dimensional data. In particular, we study the $k$-Euclidean Metric Violation problem ($\textsf{$k$-EMV}$), where the input is $D \in \mathbb{R}^{\binom{n}{2}}_{\geq 0}$ and the goal is to find the closest vector $X \in \mathbb{M}_{k}$, where $\mathbb{M}_k \subset \mathbb{R}^{\binom{n}{2}}_{\geq 0}$ is the set of all $k$-dimensional Euclidean metrics on $n$ points, and closeness is formulated as the following optimization problem, where $\| \cdot \|$ is the entry-wise $\ell_2$ norm: \[ \textsf{OPT}_{\textrm{EMV}} = \min_{X \in \mathbb{M}_{k} } \Vert D - X \Vert_2^2\,.\] Cayton and Dasgupta [CD'06] showed that this problem is NP-Hard, even when $k=1$. Dhamdhere [Dha'04] obtained a $O(\log(n))$-approximation for $\textsf{$1$-EMV}$ and leaves finding a PTAS for it as an open question (reiterated recently by Lee [Lee'25]). Although $\textsf{$k$-EMV}$ has been studied in the statistics community for over 70 years, under the name "multi-dimensional scaling", there are no known efficient approximation algorithms for $k > 1$, to the best of our knowledge. We provide the first polynomial-time additive approximation scheme for $\textsf{$k$-EMV}$. In particular, we obtain an embedding with objective value $\textsf{OPT}_{\textrm{EMV}} + \varepsilon \Vert D\Vert_2^2$ in $(n\cdot B)^{\mathsf{poly}(k, \varepsilon^{-1})}$ time, where each entry in $D$ can be represented by $B$ bits. We believe our algorithm is a crucial first step towards obtaining a PTAS for $\textsf{$k$-EMV}$. Our key technical contribution is a new analysis of correlation rounding for Sherali-Adams / Sum-of-Squares relaxations, tailored to low-dimensional embeddings. We also show that our techniques allow us to obtain additive approximation schemes for two related problems: a weighted variant of $\textsf{$k$-EMV}$ and $\ell_p$ low-rank approximation for $p>2$.

cs.DS↗

arXiv2025

Rescaled Influence Functions: Accurate Data Attribution in High Dimension

How does the training data affect a model's behavior? This is the question we seek to answer with data attribution. The leading practical approaches to data attribution are based on influence functions (IF). IFs utilize a first-order Taylor approximation to efficiently predict the effect of removing a set of samples from the training set without retraining the model, and are used in a wide variety of machine learning applications. However, especially in the high-dimensional regime (# params $\geq Ω($# samples$)$), they are often imprecise and tend to underestimate the effect of sample removals, even for simple models such as logistic regression. We present rescaled influence functions (RIF), a new tool for data attribution which can be used as a drop-in replacement for influence functions, with little computational overhead but significant improvement in accuracy. We compare IF and RIF on a range of real-world datasets, showing that RIFs offer significantly better predictions in practice, and present a theoretical analysis explaining this improvement. Finally, we present a simple class of data poisoning attacks that would fool IF-based detections but would be detected by RIF.

cs.LG↗

arXiv2025

Metric Embeddings Beyond Bi-Lipschitz Distortion via Sherali-Adams

Metric embeddings are a widely used method in algorithm design, where generally a ``complex'' metric is embedded into a simpler, lower-dimensional one. Historically, the theoretical computer science community has focused on bi-Lipschitz embeddings, which guarantee that every pairwise distance is approximately preserved. In contrast, alternative embedding objectives that are commonly used in practice avoid bi-Lipschitz distortion; yet these approaches have received comparatively less study in theory. In this paper, we focus on Multi-dimensional Scaling (MDS), where we are given a set of non-negative dissimilarities $\{d_{i,j}\}_{i,j\in [n]}$ over $n$ points, and the goal is to find an embedding $\{x_1,\dots,x_n\} \subset R^k$ that minimizes $$\textrm{OPT}=\min_{x}\mathbb{E}_{i,j\in [n]}\left(1-\frac{\|x_i - x_j\|}{d_{i,j}}\right)^2.$$ Despite its popularity, our theoretical understanding of MDS is extremely limited. Recently, Demaine et. al. (arXiv:2109.11505) gave the first approximation algorithm with provable guarantees for this objective, which achieves an embedding in constant dimensional Euclidean space with cost $\textrm{OPT} +ε$ in $n^2\cdot 2^{\textrm{poly}(Δ/ε)}$ time, where $Δ$ is the aspect ratio of the input dissimilarities. For metrics that admit low-cost embeddings, $Δ$ scales polynomially in $n$. In this work, we give the first approximation algorithm for MDS with quasi-polynomial dependency on $Δ$: for constant dimensional Euclidean space, we achieve a solution with cost $O(\log Δ)\cdot \textrm{OPT}^{Ω(1)}+ε$ in time $n^{O(1)} \cdot 2^{\text{poly}((\log(Δ)/ε))}$. Our algorithms are based on a novel geometry-aware analysis of a conditional rounding of the Sherali-Adams LP Hierarchy, allowing us to avoid exponential dependency on the aspect ratio, which would typically result from this rounding.

cs.DS↗

arXiv2024

SoS Certificates for Sparse Singular Values and Their Applications: Robust Statistics, Subspace Distortion, and More

We study $\textit{sparse singular value certificates}$ for random rectangular matrices. If $M$ is an $n \times d$ matrix with independent Gaussian entries, we give a new family of polynomial-time algorithms which can certify upper bounds on the maximum of $\|M u\|$, where $u$ is a unit vector with at most $ηn$ nonzero entries for a given $η\in (0,1)$. This basic algorithmic primitive lies at the heart of a wide range of problems across algorithmic statistics and theoretical computer science. Our algorithms certify a bound which is asymptotically smaller than the naive one, given by the maximum singular value of $M$, for nearly the widest-possible range of $n,d,$ and $η$. Efficiently certifying such a bound for a range of $n,d$ and $η$ which is larger by any polynomial factor than what is achieved by our algorithm would violate lower bounds in the SQ and low-degree polynomials models. Our certification algorithm makes essential use of the Sum-of-Squares hierarchy. To prove the correctness of our algorithm, we develop a new combinatorial connection between the graph matrix approach to analyze random matrices with dependent entries, and the Efron-Stein decomposition of functions of independent random variables. As applications of our certification algorithm, we obtain new efficient algorithms for a wide range of well-studied algorithmic tasks. In algorithmic robust statistics, we obtain new algorithms for robust mean and covariance estimation with tradeoffs between breakdown point and sample complexity, which are nearly matched by SQ and low-degree polynomial lower bounds (that we establish). We also obtain new polynomial-time guarantees for certification of $\ell_1/\ell_2$ distortion of random subspaces of $\mathbb{R}^n$ (also with nearly matching lower bounds), sparse principal component analysis, and certification of the $2\rightarrow p$ norm of a random matrix.

cs.DS↗

arXiv2024

SoS Certifiability of Subgaussian Distributions and its Algorithmic Applications

We prove that there is a universal constant $C>0$ so that for every $d \in \mathbb N$, every centered subgaussian distribution $\mathcal D$ on $\mathbb R^d$, and every even $p \in \mathbb N$, the $d$-variate polynomial $(Cp)^{p/2} \cdot \|v\|_{2}^p - \mathbb E_{X \sim \mathcal D} \langle v,X\rangle^p$ is a sum of square polynomials. This establishes that every subgaussian distribution is \emph{SoS-certifiably subgaussian} -- a condition that yields efficient learning algorithms for a wide variety of high-dimensional statistical tasks. As a direct corollary, we obtain computationally efficient algorithms with near-optimal guarantees for the following tasks, when given samples from an arbitrary subgaussian distribution: robust mean estimation, list-decodable mean estimation, clustering mean-separated mixture models, robust covariance-aware mean estimation, robust covariance estimation, and robust linear regression. Our proof makes essential use of Talagrand's generic chaining/majorizing measures theorem.

cs.DS↗

arXiv2024

Robustness Auditing for Linear Regression: To Singularity and Beyond

It has recently been discovered that the conclusions of many highly influential econometrics studies can be overturned by removing a very small fraction of their samples (often less than $0.5\%$). These conclusions are typically based on the results of one or more Ordinary Least Squares (OLS) regressions, raising the question: given a dataset, can we certify the robustness of an OLS fit on this dataset to the removal of a given number of samples? Brute-force techniques quickly break down even on small datasets. Existing approaches which go beyond brute force either can only find candidate small subsets to remove (but cannot certify their non-existence) [BGM20, KZC21], are computationally intractable beyond low dimensional settings [MR22], or require very strong assumptions on the data distribution and too many samples to give reasonable bounds in practice [BP21, FH23]. We present an efficient algorithm for certifying the robustness of linear regressions to removals of samples. We implement our algorithm and run it on several landmark econometrics datasets with hundreds of dimensions and tens of thousands of samples, giving the first non-trivial certificates of robustness to sample removal for datasets of dimension $4$ or greater. We prove that under distributional assumptions on a dataset, the bounds produced by our algorithm are tight up to a $1 + o(1)$ multiplicative factor.

cs.LG↗

arXiv2024

Robustness Implies Privacy in Statistical Estimation

We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics. We give the first black-box reduction from privacy to robustness which can produce private estimators with optimal tradeoffs among sample complexity, accuracy, and privacy for a wide range of fundamental high-dimensional parameter estimation problems, including mean and covariance estimation. We show that this reduction can be implemented in polynomial time in some important special cases. In particular, using nearly-optimal polynomial-time robust estimators for the mean and covariance of high-dimensional Gaussians which are based on the Sum-of-Squares method, we design the first polynomial-time private estimators for these problems with nearly-optimal samples-accuracy-privacy tradeoffs. Our algorithms are also robust to a nearly optimal fraction of adversarially-corrupted samples.

cs.DS↗

arXiv2024

Adversarially-Robust Inference on Trees via Belief Propagation

We introduce and study the problem of posterior inference on tree-structured graphical models in the presence of a malicious adversary who can corrupt some observed nodes. In the well-studied broadcasting on trees model, corresponding to the ferromagnetic Ising model on a $d$-regular tree with zero external field, when a natural signal-to-noise ratio exceeds one (the celebrated Kesten-Stigum threshold), the posterior distribution of the root given the leaves is bounded away from $\mathrm{Ber}(1/2)$, and carries nontrivial information about the sign of the root. This posterior distribution can be computed exactly via dynamic programming, also known as belief propagation. We first confirm a folklore belief that a malicious adversary who can corrupt an inverse-polynomial fraction of the leaves of their choosing makes this inference impossible. Our main result is that accurate posterior inference about the root vertex given the leaves is possible when the adversary is constrained to make corruptions at a $ρ$-fraction of randomly-chosen leaf vertices, so long as the signal-to-noise ratio exceeds $O(\log d)$ and $ρ\leq c \varepsilon$ for some universal $c > 0$. Since inference becomes information-theoretically impossible when $ρ\gg \varepsilon$, this amounts to an information-theoretically optimal fraction of corruptions, up to a constant multiplicative factor. Furthermore, we show that the canonical belief propagation algorithm performs this inference.

cs.DS↗

arXiv2024

Beyond Catoni: Sharper Rates for Heavy-Tailed and Robust Mean Estimation

We study the fundamental problem of estimating the mean of a $d$-dimensional distribution with covariance $Σ\preccurlyeq σ^2 I_d$ given $n$ samples. When $d = 1$, \cite{catoni} showed an estimator with error $(1+o(1)) \cdot σ\sqrt{\frac{2 \log \frac{1}δ}{n}}$, with probability $1 - δ$, matching the Gaussian error rate. For $d>1$, a natural estimator outputs the center of the minimum enclosing ball of one-dimensional confidence intervals to achieve a $1-δ$ confidence radius of $\sqrt{\frac{2 d}{d+1}} \cdot σ\left(\sqrt{\frac{d}{n}} + \sqrt{\frac{2 \log \frac{1}δ}{n}}\right)$, incurring a $\sqrt{\frac{2d}{d+1}}$-factor loss over the Gaussian rate. When the $\sqrt{\frac{d}{n}}$ term dominates by a $\sqrt{\log \frac{1}δ}$ factor, \cite{lee2022optimal-highdim} showed an improved estimator matching the Gaussian rate. This raises a natural question: Is the $\sqrt{\frac{2 d}{d+1}}$ loss \emph{necessary} when the $\sqrt{\frac{2 \log \frac{1}δ}{n}}$ term dominates? We show that the answer is \emph{no} -- we construct an estimator that improves over the above naive estimator by a constant factor. We also consider robust estimation, where an adversary is allowed to corrupt an $ε$-fraction of samples arbitrarily: in this case, we show that the above strategy of combining one-dimensional estimates and incurring the $\sqrt{\frac{2d}{d+1}}$-factor \emph{is} optimal in the infinite-sample limit.

math.ST↗

arXiv2023

Towards Practical Robustness Auditing for Linear Regression

We investigate practical algorithms to find or disprove the existence of small subsets of a dataset which, when removed, reverse the sign of a coefficient in an ordinary least squares regression involving that dataset. We empirically study the performance of well-established algorithmic techniques for this task -- mixed integer quadratically constrained optimization for general linear regression problems and exact greedy methods for special cases. We show that these methods largely outperform the state of the art and provide a useful robustness check for regression problems in a few dimensions. However, significant computational bottlenecks remain, especially for the important task of disproving the existence of such small sets of influential samples for regression problems of dimension $3$ or greater. We make some headway on this challenge via a spectral algorithm using ideas drawn from recent innovations in algorithmic robust statistics. We summarize the limitations of known techniques in several challenge datasets to encourage further algorithmic innovation.

stat.ME↗

arXiv2023

The Full Landscape of Robust Mean Testing: Sharp Separations between Oblivious and Adaptive Contamination

We consider the question of Gaussian mean testing, a fundamental task in high-dimensional distribution testing and signal processing, subject to adversarial corruptions of the samples. We focus on the relative power of different adversaries, and show that, in contrast to the common wisdom in robust statistics, there exists a strict separation between adaptive adversaries (strong contamination) and oblivious ones (weak contamination) for this task. Specifically, we resolve both the information-theoretic and computational landscapes for robust mean testing. In the exponential-time setting, we establish the tight sample complexity of testing $\mathcal{N}(0,I)$ against $\mathcal{N}(αv, I)$, where $\|v\|_2 = 1$, with an $\varepsilon$-fraction of adversarial corruptions, to be \[ \tildeΘ\!\left(\max\left(\frac{\sqrt{d}}{α^2}, \frac{d\varepsilon^3}{α^4},\min\left(\frac{d^{2/3}\varepsilon^{2/3}}{α^{8/3}}, \frac{d \varepsilon}{α^2}\right)\right) \right) \,, \] while the complexity against adaptive adversaries is \[ \tildeΘ\!\left(\max\left(\frac{\sqrt{d}}{α^2}, \frac{d\varepsilon^2}{α^4} \right)\right) \,, \] which is strictly worse for a large range of vanishing $\varepsilon,α$. To the best of our knowledge, ours is the first separation in sample complexity between the strong and weak contamination models. In the polynomial-time setting, we close a gap in the literature by providing a polynomial-time algorithm against adaptive adversaries achieving the above sample complexity $\tildeΘ(\max({\sqrt{d}}/{α^2}, {d\varepsilon^2}/{α^4} ))$, and a low-degree lower bound (which complements an existing reduction from planted clique) suggesting that all efficient algorithms require this many samples, even in the oblivious-adversary setting.

cs.DS↗

arXiv2022

Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation

We establish a simple connection between robust and differentially-private algorithms: private mechanisms which perform well with very high probability are automatically robust in the sense that they retain accuracy even if a constant fraction of the samples they receive are adversarially corrupted. Since optimal mechanisms typically achieve these high success probabilities, our results imply that optimal private mechanisms for many basic statistics problems are robust. We investigate the consequences of this observation for both algorithms and computational complexity across different statistical problems. Assuming the Brennan-Bresler secret-leakage planted clique conjecture, we demonstrate a fundamental tradeoff between computational efficiency, privacy leakage, and success probability for sparse mean estimation. Private algorithms which match this tradeoff are not yet known -- we achieve that (up to polylogarithmic factors) in a polynomially-large range of parameters via the Sum-of-Squares method. To establish an information-computation gap for private sparse mean estimation, we also design new (exponential-time) mechanisms using fewer samples than efficient algorithms must use. Finally, we give evidence for privacy-induced information-computation gaps for several other statistics and learning problems, including PAC learning parity functions and estimation of the mean of a multivariate Gaussian.

stat.ML↗