We develop a new approach for clustering non-spherical (i.e., arbitrary component covariances) Gaussian mixture models via a subroutine based on the sum-of-squares method that finds a low-dimensional separation-preserving projection of the input data. Our method provides a non-spherical analog of the classical dimension reduction based on singular value decomposition that, among several other applications, forms a key component of the celebrated spherical clustering algorithm of Vempala and Wang (2004). As applications, we obtain an algorithm to (1) cluster an arbitrary total-variation separated mixture of $k$ centered (i.e., zero-mean) Gaussians with $n\geq \mathrm{poly}(d) f(w_{\min}^{-1})$ samples and $\mathrm{poly}(n)$ time, and (2) cluster an arbitrary total-variation separated mixture of $k$ Gaussians with identical but arbitrary unknown covariance with $n \geq d^{O(\log w_{\min}^{-1})} f(w_{\min}^{-1})$ samples and $n^{O(\log w_{\min}^{-1})}$ time. Here, $w_{\min}$ is the minimum mixing weight of the input mixture, and $f$ does not depend on the dimension $d$. Our algorithms naturally extend to tolerate a dimension-independent fraction of arbitrary outliers. Before this work, the techniques in the state-of-the-art non-spherical clustering algorithms needed $d^{O(k)} f(w_{\min}^{-1})$ samples and time for clustering such mixtures. Our results may come as a surprise in the context of the $d^{\Omega(k)}$ statistical query and sum-of-squares lower bounds (Diakonikolas et al. (2017, 2024)) for clustering non-spherical Gaussian mixtures. While these results are usually thought to rule out $d^{o(k)}$ cost algorithms for the problem, our results show that the lower bounds can, in fact, be circumvented for a remarkably general class of Gaussian mixtures.

Mitali Bafna, Karthik C. S., and Dor Minzer. 2025. Near Optimal Constant Inapproximability under ETH for Fundamental Problems in Parameterized Complexity. In Proceedings of the 57th Annual ACM Symposium on Theory of Computing (STOC '25). Association for Computing Machinery, New York, NY, USA, 2118–2129.

We study the complexity of affine Unique-Games (UG) over globally hypercontractive graphs, which are graphs that are not small set expanders but admit a useful and succinct characterization of all small sets that violate the small-set expansion property. This class of graphs includes the Johnson and Grassmann graphs, which have played a pivotal role in recent PCP constructions for UG, and their generalizations via high-dimensional expanders. We show new rounding techniques for higher degree sum-of-squares (SoS) relaxations for worst-case optimization. In particular, our algorithm shows how to round "low-entropy" pseudodistributions, broadly extending the algorithmic framework of [Mitali Bafna et al., 2021]. At a high level, [Mitali Bafna et al., 2021] showed how to round pseudodistributions for problems where there is a "unique" good solution. We extend their framework by exhibiting a rounding for problems where there might be "few good solutions". Our result suggests that UG is easy on globally hypercontractive graphs, and therefore highlights the importance of graphs that lack such a characterization in the context of PCP reductions for UG.

Let$X$be a d-dimensional simplicial complex. A function$F: X(k)\rightarrow\{0,1\}^{k}$is said to be a direct product function if there exists a function$f: x(1)\rightarrow\{0,1\}$such that$F(\sigma)=(f(\sigma_{1}),\ \ldots,\ f(\sigma_{k}))$for each k-face$\sigma$, In an effort to simplify components of the PCP theorem, Goldreich and Safra [1] introduced the problem of direct product testing, which asks whether one can test if$F: X(k)\rightarrow\{0,1\}^{k}$- is correlated with a direct product function by querying$F$on only 2 inputs. Dinur and Kaufman [2] conjectured that there exist bounded degree complexes with a direct product test in the small soundness regime. We resolve their conjecture by showing that for all$\delta > 0$, there exists a family of high-dimensional expanders with degree$O_{\delta}(1)$and a 2-query direct product tester with soundness$\delta$We use the characterization given by [3] and independently by [4], who showed that some form of non-Abelian coboundary expansion (which they called “Unique-Games coboundary expansion”) is a necessary and sufficient condition for a complex to admit such direct product testers. Our main technical contribution is a general technique for showing coboundary expansion of complexes with coefficients in a non-Abelian group. This allows us to prove that the high dimensional expanders constructed by [5] satisfy the conditions of [3], thus admitting a 2-query direct product tester with small soundness.

A d-dimensional simplicial complex X is said to support a direct product tester if any locally consistent function defined on its k-faces (where k≪ d) necessarily come from a function over its vertices. More precisely, a direct product tester has a distribution µ over pairs of k-faces (A,A′), and given query access to F: X(k)→{0,1}k it samples (A,A′)∼ µ and checks that F[A]|A∩ A′ = F[A′]|A∩ A′. The tester should have (1) the ”completeness property”, meaning that any assignment F which is a direct product assignment passes the test with probability 1, and (2) the ”soundness property”, meaning that if F passes the test with probability s, then F must be correlated with a direct product function. Dinur and Kaufman showed that a sufficiently good spectral expanding complex X admits a direct product tester in the ”high soundness” regime where s is close to 1. They asked whether there are high dimensional expanders that support direct product tests in the ”low soundness”, when s is close to 0. We give a characterization of high-dimensional expanders that support a direct product tester in the low soundness regime. We show that spectral expansion is insufficient, and the complex must additionally satisfy a variant of coboundary expansion, which we refer to as ”Unique-Games coboundary expanders”. Conversely, we show that this property is also sufficient to get direct product testers. This property can be seen as a high-dimensional generalization of the standard notion of coboundary expansion over non-Abelian groups for 2-dimensional complexes. It asserts that any locally consistent Unique-Games instance obtained using the low-level faces of the complex, must admit a good global solution.

We give efficient algorithms for finding power-sum decomposition of an input polynomial $P(x)=\displaystyle \sum_{i\leq m}p_{i}(x)^{d}$ with component $p_{i}s$. The case of linear $p_{i}s$ is equivalent to the well-studied tensor decomposition problem while the quadratic case occurs naturally in studying identifiability of non-spherical Gaussian mixtures from low-order moments. Unlike tensor decomposition, both the unique identifiability and algorithms for this problem are not well-understood. For the simplest setting of quadratic $p_{i}s$ and $d=3$, prior work of [11] yields an algorithm only when $m\leq\overline{O}(\sqrt{n})$. On the other hand, the more general recent result of [13] builds an algebraic approach to handle any $m=n^{O(1)}$ components but only when d is large enough (while yielding no bounds for d=3 or even d=100) and only handles an inverse exponential noise. Our results obtain a substantial quantitative improvement on both the prior works above even in the base case of d=3 and quadratic $p_{i}s$. Specifically, our algorithm succeeds in decomposing a sum of $m\sim\overline{O}(n)$ generic quadratic $p_{i}s$ for $d=3$ and more generally the dth power-sum of $m\sim n^{2d/15}$ generic degree-K polynomials for any K$\geq$2. Our algorithm relies only on basic numerical linear algebraic primitives, is exact (i.e., obtain arbitrarily tiny error up to numerical precision), and handles an inverse polynomial noise when the $p_{i}s$ have random Gaussian coefficients. Our main tool is a new method for extracting the linear span of $p_{i}s$ by studying the linear subspace of low-order partial derivatives of the input P. For establishing polynomial stability of our algorithm in average-case, we prove inverse polynomial bounds on the smallest singular value of certain correlated random matrices with low-degree polynomial entries that arise in our analyses. Since previous techniques only yield significantly weaker bounds, we analyze the smallest singular value of matrices by studying the largest singular value of certain deviation matrices via graph matrix decomposition and the trace moment method.

Higher order random walks (HD-walks) on high dimensional expanders (HDX) have seen an incredible amount of study and application since their introduction by Kaufman and Mass (ITCS 2016), yet their broader combinatorial and spectral properties remain poorly understood. We develop a combinatorial characterization of the spectral structure of HD-walks on two-sided local-spectral expanders (Dinur and Kaufman FOCS 2017), which offer a broad generalization of the well-studied Johnson and Grassmann graphs. Our characterization, which shows that the spectra of HD-walks lie tightly concentrated in a few combinatorially structured strips, leads to novel structural theorems such as a tight ℓ2-characterization of edge-expansion, as well as to a new understanding of local-to-global graph algorithms on HDX. Towards the latter, we introduce a novel spectral complexity measure called Stripped Threshold Rank, and show how it can replace the (much larger) threshold rank as a parameter controlling the performance of algorithms on structured objects. Combined with a sum-of-squares proof for the former ℓ2-characterization, we give a concrete application of this framework to algorithms for unique games on HD-walks, where in many cases we improve the state of the art (Barak, Raghavendra, and Steurer FOCS 2011, and Arora, Barak, and Steurer JACM 2015) from nearly-exponential to polynomial time (e.g. for sparsifications of Johnson graphs or of slices of the q-ary hypercube). Our characterization of expansion also holds an interesting connection to hardness of approximation, where an ℓ∞-variant for the Grassmann graphs was recently used to resolve the 2-2 Games Conjecture (Khot, Minzer, and Safra FOCS 2018). We give a reduction from a related ℓ∞-variant to our ℓ2-characterization, but it loses factors in the regime of interest for hardness where the gap between ℓ2 and ℓ∞ structure is large. Nevertheless, our results open the door for further work on the use of HDX in hardness of approximation and their general relation to unique games.

Hypercontractivity is one of the most powerful tools in Boolean function analysis. Originally studied over the discrete hypercube, recent years have seen increasing interest in extensions to settings like the p-biased cube, slice, or Grassmannian, where variants of hypercontractivity have found a number of breakthrough applications including the resolution of Khot’s 2-2 Games Conjecture (Khot, Minzer, Safra FOCS 2018). In this work, we develop a new theory of hypercontractivity on high dimensional expanders (HDX), an important class of expanding complexes that has recently seen similarly impressive applications in both coding theory and approximate sampling. Our results lead to a new understanding of the structure of Boolean functions on HDX, including a tight analog of the KKL Theorem and a new characterization of non-expanding sets.

The problem of solving linear systems is one of the most fundamental problems in computer science, where given a satisfiable linear system (A,b), for A ∈ ℝ^{n×n} and b ∈ ℝⁿ, we wish to find a vector x ∈ ℝⁿ such that Ax = b. The current best algorithms for solving dense linear systems reduce the problem to matrix multiplication, and run in time O(n^ω). We consider the problem of finding ε-approximate solutions to linear systems with respect to the L₂-norm, that is, given a satisfiable linear system (A ∈ ℝ^{n×n}, b ∈ ℝⁿ), find an x ∈ ℝⁿ such that ||Ax - b||₂ ≤ ε||b||₂. Our main result is a fine-grained reduction from computing the rank of a matrix to finding ε-approximate solutions to linear systems. In particular, if the best known Õ(n^ω) time algorithm for computing the rank of n × O(n) matrices is optimal (which we conjecture is true), then finding an ε-approximate solution to a dense linear system also requires Ω̃(n^ω) time, even for ε as large as (1 - 1/poly(n)). We also prove (under some modified conjectures for the rank-finding problem) optimal hardness of approximation for sparse linear systems, linear systems over positive semidefinite matrices and well-conditioned linear systems. At the heart of our results is a novel reduction from the rank problem to a decision version of the approximate linear systems problem. This reduction preserves properties such as matrix sparsity and bit complexity.

We give an algorithm for solving unique games (UG) instances whenever low-degree sum-of-squares proofs certify good bounds on the small-set-expansion of the underlying constraint graph via a hypercontractive inequality. Our algorithm is in fact more versatile, and succeeds even when the constraint graph is not a small-set expander as long as the structure of non-expanding small sets is (informally speaking) “characterized” by a low-degree sum-of-squares proof. Our results are obtained by rounding low-entropy solutions — measured via a new global potential function — to sum-of-squares (SoS) semidefinite programs. This technique adds to the (currently short) list of general tools for analyzing SoS relaxations for worst-case optimization problems.

Using graph clustering, we improve accuracy of Kronecker social networks which are protected by differential privacy. Ensuring the differential privacy implicates addition of marginal changes to the network and publishing the modified network data. In many cases, it induces a large gap between the original network and the modified graph statistics, such that very little useful information can be inferred from the published graph. We use the fact that network structures in all graph clusters are similar, to improve the utility of the publication methods based on Kronecker graphs. Instead of anonymizing the social network as a whole, we anonymize each cluster of the network separately, and combine the sanitized results thereafter. We justify why this idea provides an anonymized social network with high utility and also prove that our output social network ensures rigorous differential privacy guarantees. Our experimental results show that our mechanism exhibits good agreement of the structural properties with the real graphs, and outperforms the existing anonymization techniques for certain utility measures.

We study the role of perfect completeness in probabilistically checkable proof systems (PCPs) and give a way to transform a PCP with imperfect completeness to one with perfect completeness, when the initial gap is a constant. We show that PCP_{c,s}[r,q] subseteq PCP_{1,s'}[r+O(1),q+O(r)] for c-s=Omega(1) which in turn implies that one can convert imperfect completeness to perfect in linear-sized PCPs for NP with a O(log n) additive loss in the query complexity q. We show our result by constructing a "robust circuit" using threshold gates. These results are a gap amplification procedure for PCPs, (when completeness is not 1) analogous to questions studied in parallel repetition [Anup Rao, 2011] and pseudorandomness [David Gillman, 1998] and might be of independent interest. We also investigate the time-complexity of approximating perfectly satisfiable instances of 3SAT versus those with imperfect completeness. We show that the Gap-ETH conjecture without perfect completeness is equivalent to Gap-ETH with perfect completeness, i.e. MAX 3SAT(1-epsilon,1-delta), delta > epsilon has 2^{o(n)} algorithms if and only if MAX 3SAT(1,1-delta) has 2^{o(n)} algorithms. We also relate the time complexities of these two problems in a more fine-grained way to show that T_2(n) <= T_1(n(log log n)^{O(1)}), where T_1(n),T_2(n) denote the randomized time-complexity of approximating MAX 3SAT with perfect and imperfect completeness respectively.

We study the role of interaction in the Common Randomness Generation (CRG) and Secret Key Generation (SKG) problems. In the CRG problem, two players, Alice and Bob, respectively get samples X1, X2, … and Y1, Y2, … with the pairs (X1, Y1), (X2, Y2), … being drawn independently from some known probability distribution µ. They wish to communicate so as to agree on L bits of randomness. The SKG problem is the restriction of the CRG problem to the case where the key is required to be close to random even to an eavesdropper who can listen to their communication (but does not have access to the inputs of Alice and Bob). In this work, we study the relationship between the amount of communication and the number of rounds of interaction in both the CRG and the SKG problems. Specifically, we construct a family of distributions µ = µr,n,L, parametrized by integers r, n and L, such that for every r there exists a constant b = b(r) for which CRG (respectively SKG) is feasible when (Xi, Yi) ∼ µr,n,L with r + 1 rounds of communication, each consisting of O(log n) bits, but when restricted to r/2 – 2 rounds of interaction, the total communication must exceed Ω(n/ logb(n)) bits. Prior to our work no separations were known for r ≥ 2.

We give a new algorithm for approximating the Discrete Fourier transform of an approximately sparse signal that is robust to worst-case $L_0$ corruptions, namely that some coordinates of the signal can be corrupt arbitrarily. Our techniques generalize to a wide range of linear transformations that are used in data analysis such as the Discrete Cosine and Sine transforms, the Hadamard transform, and their high-dimensional analogs. We use our algorithm to successfully defend against worst-case $L_0$ adversaries in the setting of image classification. We give experimental results on the Jacobian-based Saliency Map Attack (JSMA) and the CW $L_0$ attack on the MNIST and Fashion-MNIST datasets as well as the Adversarial Patch on the ImageNet dataset.

In the differentially private top-$k$ selection problem, we are given a dataset $X ∈\pmo^n \times d$, in which each row belongs to an individual and each column corresponds to some binary attribute, and our goal is to find a set of $k ≪d$ columns whose means are approximately as large as possible. Differential privacy requires that our choice of these $k$ columns does not depend too much on any on individual’s dataset. This problem can be solved using the well known exponential mechanism and composition properties of differential privacy. In the high-accuracy regime, where we require the error of the selection procedure to be to be smaller than the so-called sampling error $α≈\sqrt\ln(d)/n$, this procedure succeeds given a dataset of size $n ≳k \ln(d)$. We prove a matching lower bound, showing that a dataset of size $n ≳k \ln(d)$ is necessary for private top-$k$ selection in this high-accuracy regime. Our lower bound shows that selecting the $k$ largest columns requires more data than simply estimating the value of those $k$ columns, which can be done using a dataset of size just $n ≳k$.

Various combinatorial/algebraic parameters are used to quantify the complexity of a Boolean function. Among them, sensitivity is one of the simplest and block sensitivity is one of the most useful. Nisan (1989) and Nisan and Szegedy (1991) showed that block sensitivity and several other parameters, such as certificate complexity, decision tree depth, and degree over R, are all polynomially related to one another. The sensitivity conjecture states that there is also a polynomial relationship between sensitivity and block sensitivity, thus supplying the "missing link". Since its introduction in 1991, the sensitivity conjecture has remained a challenging open question in the study of Boolean functions. One natural approach is to prove it for special classes of functions. For instance, the conjecture is known to be true for monotone functions, symmetric functions, and functions describing graph properties. In this paper, we consider the conjecture for Boolean functions computable by read-k formulas. A read-k formula is a tree in which each variable appears at most k times among the leaves and has Boolean gates at its internal nodes. We show that the sensitivity conjecture holds for read-once formulas with gates computing symmetric functions. We next consider regular formulas with OR and AND gates. A formula is regular if it is a leveled tree with all gates at a given level having the same fan-in and computing the same function. We prove the sensitivity conjecture for constant depth regular read-k formulas for constant k.