We establish two new direct product theorems for the randomized query complexity of Boolean functions. The first shows that computing n copies of a function f, even with a small success probability of $\gamma^{n}$, requires $\Theta(n)$ times the maximum distributional query complexity of f with success parameter $\gamma$. This result holds for all success parameters $\gamma$, even when $\gamma$ is very close to 1/2 or to 1. As a result, it unifies and generalizes Drucker’s direct product theorem (2012) for $\gamma$ bounded away from $\frac{1}{2}$ and 1 as well as the strong direct sum theorem of Blais and Brody (2019) for $\gamma \approx 1-1 / n$. The second establishes a general list decoding direct product theorem that captures many different variants of “partial computation” tasks related to the function $f^{n}$ consisting of n copies of f. Notably, our list decoding direct product theorem yields a new threshold direct product theorem and other new variants such as the labelled-threshold direct product theorem. Both of these direct product theorems are obtained by taking a new approach. Instead of directly analyzing the query complexity of algorithms, we introduce a new measure of complexity of functions that we call discounted score. We show that this measure satisfies a number of useful structural properties, including tensorization, that make it particularly suitable for the study of direct product questions.

Abstract. We establish nearly optimal sample complexity bounds for testing the [Formula: see text]-clique property in the dense graph model. Specifically, we show that it is possible to distinguish graphs on [Formula: see text] vertices that have a [Formula: see text]-clique from graphs for which at least [Formula: see text] edges must be added to form a [Formula: see text]-clique by sampling and inspecting a random subgraph on only [Formula: see text] vertices. We also establish new sample complexity bounds for [Formula: see text]-testing [Formula: see text]-colorability. In this case, we show that a sampled subgraph on [Formula: see text] vertices suffices to distinguish [Formula: see text]-colorable graphs from those for which any [Formula: see text]-coloring of the vertices causes at least [Formula: see text] edges to be monochromatic. The new bounds for testing the [Formula: see text]-clique and [Formula: see text]-colorability properties are both obtained via new extensions of the graph container method. This method has been an effective tool for tackling various problems in graph theory and combinatorics. Our results demonstrate that it is also a powerful tool for the analysis of property testing algorithms.

We study the problems of testing and learning high-dimensional discrete convex sets. The simplest high-dimensional discrete domain where convexity is a non-trivial property is the ternary hypercube, {-1,0,1}ⁿ. The goal of this work is to understand structural combinatorial properties of convex sets in this domain and to determine the complexity of the testing and learning problems. We obtain the following results. Structural: We prove nearly tight bounds on the edge boundary of convex sets in {0,±1}ⁿ, showing that the maximum edge boundary of a convex set is Õ(n^{3/4})⋅3ⁿ, or equivalently that every convex set has influence Õ(n^{3/4}) and a convex set exists with influence Ω(n^{3/4}). Learning and sample-based testing: We prove upper and lower bounds of 3^{Õ(n^{3/4})} and 3^{Ω(√n)} for the task of learning convex sets under the uniform distribution from random examples. The analysis of the learning algorithm relies on our upper bound on the influence. Both the upper and lower bound also hold for the problem of sample-based testing with two-sided error. For sample-based testing with one-sided error we show that the sample-complexity is 3^{Θ(n)}. Testing with queries: We prove nearly matching upper and lower bounds of 3^{Θ̃(√n)} for one-sided error testing of convex sets with non-adaptive queries.

The graph and hypergraph container methods are powerful tools with a wide range of applications across combinatorics. Recently, Blais and Seth (FOCS 2023) showed that the graph container method is particularly well-suited for the analysis of the natural canonical tester for two fundamental graph properties: having a large independent set and k-colorability. In this work, we show that the connection between the container method and property testing extends further along two different directions.

We establish nearly optimal sample complexity bounds for testing the $\rho$-clique property in the dense graph model. Specifically, we show that it is possible to distinguish graphs on n vertices that have a $\rho n$-clique from graphs for which at least $\epsilon n^{2}$ edges must be added to form a $\rho n$-clique by sampling and inspecting a random subgraph on only $\tilde{O}\left(\rho^{3} / \epsilon^{2}\right)$ vertices. We also establish new sample complexity bounds for $\epsilon$-testing k-colorability. In this case, we show that a sampled subgraph on $\tilde{O}(k / \epsilon)$ vertices suffices to distinguish k-colorable graphs from those for which any k-coloring of the vertices causes at least $\epsilon n^{2}$ edges to be monochromatic. The new bounds for testing the $\rho$-clique and k-colorability properties are both obtained via new extensions of the graph container method. This method has been an effective tool for tackling various problems in graph theory and combinatorics. Our results demonstrate that it is also a powerful tool for the analysis of property testing algorithms.

The celebrated minimax principle of Yao says that for any Boolean-valued function f with finite domain, there is a distribution μ over the domain of f such that computing f to error ε against inputs from μ is just as hard as computing f to error ε on worst-case inputs. Notably, however, the distribution μ depends on the target error level ε: the hard distribution which is tight for bounded error might be trivial to solve to small bias, and the hard distribution which is tight for a small bias level might be far from tight for bounded error levels. In this work, we introduce a new type of minimax theorem which can provide a hard distribution μ that works for all bias levels at once. We show that this works for randomized query complexity, randomized communication complexity, some randomized circuit models, quantum query and communication complexities, approximate polynomial degree, and approximate logrank. We also prove an improved version of Impagliazzo’s hardcore lemma. Our proofs rely on two innovations over the classical approach of using Von Neumann’s minimax theorem or linear programming duality. First, we use Sion’s minimax theorem to prove a minimax theorem for ratios of bilinear functions representing the cost and score of algorithms. Second, we introduce a new way to analyze low-bias randomized algorithms by viewing them as “forecasting algorithms” evaluated by a certain proper scoring rule. The expected score of the forecasting version of a randomized algorithm appears to be a more fine-grained way of analyzing the bias of the algorithm. We show that such expected scores have many elegant mathematical properties—for example, they can be amplified linearly instead of quadratically. We anticipate forecasting algorithms will find use in future work in which a fine-grained analysis of small-bias algorithms is required.

We prove1two results about randomised query complexity $\mathbf{R}(f)$. First, we introduce a linearised complexity measure LR and show that it satisfies an inner-optimal composition theorem: $\mathbf{R}(f^{\circ} g)\geq\Omega(\mathbf{R}(f)\mathbf{L R}(g))$ for all partial f and g, and moreover, LR is the largest possible measure with this property. In particular, LR can be polynomially larger than previous measures that satisfy an inner composition theorem, such as the max-conflict complexity of Gavinsky, Lee, Santha, and Sanyal (ICALP 2019). Our second result addresses a question of Yao (FOCS 1977). He asked if $\epsilon$-error expected query complexity $\overline{\mathbf{R}}_{\epsilon}(f)$ admits a distributional characterisation relative to some hard input distribution. Vereshchagin (TCS 1998) answered this question affirmatively in the bounded-error case. We show that an analogous theorem fails in the small-bias case $\epsilon=1/2-o(1)$.1This is an extended abstract. For the full version of this article, please refer to [BDBGM22].

Recent beyond worst-case optimal join algorithms Minesweeper and its generalization Tetris have brought the theory of indexing and join processing together by developing a geometric framework for joins. These algorithms take as input an index $\mathcal{B}$, referred to as a box cover, that stores output gaps that can be inferred from traditional indexes, such as B+ trees or tries, on the input relations. The performances of these algorithms highly depend on the certificate of $\mathcal{B}$, which is the smallest subset of gaps in $\mathcal{B}$ whose union covers all of the gaps in the output space of a query $Q$. We study how to generate box covers that contain small size certificates to guarantee efficient runtimes for these algorithms. First, given a query $Q$ over a set of relations of size $N$ and a fixed set of domain orderings for the attributes, we give a $\tilde{O}(N)$-time algorithm called GAMB which generates a box cover for $Q$ that is guaranteed to contain the smallest size certificate across any box cover for $Q$. Second, we show that finding a domain ordering to minimize the box cover size and certificate is NP-hard through a reduction from the 2 consecutive block minimization problem on boolean matrices. Our third contribution is a $\tilde{O}(N)$-time approximation algorithm called ADORA to compute domain orderings, under which one can compute a box cover of size $\tilde{O}(K^r)$, where $K$ is the minimum box cover for $Q$ under any domain ordering and $r$ is the maximum arity of any relation. This guarantees certificates of size $\tilde{O}(K^r)$. We combine ADORA and GAMB with Tetris to form a new algorithm we call TetrisReordered, which provides several new beyond worst-case bounds. On infinite families of queries, TetrisReordered's runtimes are unboundedly better than the bounds stated in prior work.

We consider the problem of determining which classes of functions can be tested more efficiently than they can be learned, in the distribution-free sample-based model that corresponds to the standard PAC learning setting. Our main result shows that while VC dimension by itself does not always provide tight bounds on the number of samples required to test a class of functions in this model, it can be combined with a closely-related variant that we call “lower VC” (or LVC) dimension to obtain strong lower bounds on this sample complexity.

We show that every algorithm for testing $n$-variate Boolean functions for monotonicity must have query complexity $\tilde{\Omega}(n^{1/4})$. All previous lower bounds for this problem were designed for nonadaptive algorithms and, as a result, the best previous lower bound for general (possibly adaptive) monotonicity testers was only $\Omega(\log n)$. Combined with the query complexity of the nonadaptive monotonicity tester of Khot, Minzer, and Safra (FOCS 2015), our lower bound shows that adaptivity can result in at most a quadratic reduction in the query complexity for testing monotonicity. By contrast, we show that there is an exponential gap between the query complexity of adaptive and nonadaptive algorithms for testing regular linear threshold functions (LTFs) for monotonicity. Chen, De, Servedio, and Tan (STOC 2015) recently showed that nonadaptive algorithms require almost $\Omega(n^{1/2})$ queries for this task. We introduce a new adaptive monotonicity testing algorithm which has query complexity $O(\log n)$ when the input is a regular LTF.

A body K ⊂ ℝⁿ is convex if and only if the line segment between any two points in K is completely contained within K or, equivalently, if and only if the convex hull of a set of points in K is contained within K. We show that neither of those characterizations of convexity are robust: there are bodies in ℝⁿ that are far from convex - in the sense that the volume of the symmetric difference between the set K and any convex set C is a constant fraction of the volume of K - for which a line segment between two randomly chosen points x,y ∈ K or the convex hull of a random set X of points in K is completely contained within K except with exponentially small probability. These results show that any algorithms for testing convexity based on the natural line segment and convex hull tests have exponential query complexity.

We prove two new results about the randomized query complexity of composed functions. First, we show that the randomized composition conjecture is false: there are families of partial Boolean functions f and g such that R(f°g) ≪ R(f)R(g). In fact, we show that the left hand side can be polynomially smaller than the right hand side (though in our construction, both sides are polylogarithmic in the input size of f). Second, we show that for all f and g, R(f°g) = Ω(noisyR(f) R(g)), where noisyR(f) is a measure describing the cost of computing f on noisy oracle inputs. We show that this composition theorem is the strongest possible of its type: for any measure M(·) satisfying R(f°g)=Ω(M(f)R(g)) for all f and g, it must hold that noisyR(f)=Ω(M(f)) for all f. We also give a clean characterization of the measure noisyR(f): it satisfies noisyR(f)=Θ(R(f°GapMajn)/R(GapMajn)), where n is the input size of f and GapMajn is the √n-gap majority function on n bits.

The celebrated minimax principle of Yao (1977) says that for any Boolean-valued function f with finite domain, there is a distribution μ over the domain of f such that computing f to error ε against inputs from μ is just as hard as computing f to error ε on worst-case inputs. Notably, however, the distribution μ depends on the target error level ε: the hard distribution which is tight for bounded error might be trivial to solve to small bias, and the hard distribution which is tight for a small bias level might be far from tight for bounded error levels. In this work, we introduce a new type of minimax theorem which can provide a hard distribution μ that works for all bias levels at once. We show that this works for randomized query complexity, randomized communication complexity, some randomized circuit models, quantum query and communication complexities, approximate polynomial degree, and approximate logrank. We also prove an improved version of Impagliazzo's hardcore lemma. Our proofs rely on two innovations over the classical approach of using Von Neumann's minimax theorem or linear programming duality. First, we use Sion's minimax theorem to prove a minimax theorem for ratios of bilinear functions representing the cost and score of algorithms. Second, we introduce a new way to analyze low-bias randomized algorithms by viewing them as “forecasting algorithms” evaluated by a certain proper scoring rule. The expected score of the forecasting version of a randomized algorithm appears to be a more fine-grained way of analyzing the bias of the algorithm. We show that such expected scores have many elegant mathematical properties: for example, they can be amplified linearly instead of quadratically. We anticipate forecasting algorithms will find use in future work in which a fine-grained analysis of small-bias algorithms is required.

We establish new upper and lower bounds on the number of queries required to test convexity of functions over various discrete domains. 1.We provide a simplified version of the non-adaptive convexity tester on the line. We re-prove the upper bound in the usual uniform model, and prove an upper bound in the distribution-free setting.2.We show a tight lower bound of queries for testing convexity of functions f: [n] → ℝ on the line. This lower bound applies to both adaptive and non-adaptive algorithms, and matches the upper bound from item 1, showing that adaptivity does not help in this setting.3.Moving to higher dimensions, we consider the case of a stripe [3] × [n]. We construct an adaptive tester for convexity of functions f: [3] × [n] → ℝ with query complexity O(log2 n). We also show that any non-adaptive tester must use queries in this setting. Thus, adaptivity yields an exponential improvement for this problem.4.For functions f: [n]d → ℝ over domains of dimension d ≥ 2, we show a non-adaptive query lower bound .

We establish two results regarding the query complexity of bounded-error randomized algorithms. Bounded-error separation theorem. There exists a total function f : {0,1}^n -> {0,1} whose epsilon-error randomized query complexity satisfies overline{R}_epsilon(f) = Omega(R(f) * log 1/epsilon). Strong direct sum theorem. For every function f and every k >= 2, the randomized query complexity of computing k instances of f simultaneously satisfies overline{R}_epsilon(f^k) = Theta(k * overline{R}_{epsilon/k}(f)). As a consequence of our two main results, we obtain an optimal superlinear direct-sum-type theorem for randomized query complexity: there exists a function f for which R(f^k) = Theta(k log k * R(f)). This answers an open question of Drucker (2012). Combining this result with the query-to-communication complexity lifting theorem of Göös, Pitassi, and Watson (2017), this also shows that there is a total function whose public-coin randomized communication complexity satisfies R^{cc}(f^k) = Theta(k log k * R^{cc}(f)), answering a question of Feder, Kushilevitz, Naor, and Nisan (1995).

A function f :{ −1,1} n → { −1,1} is a k -junta if it depends on at most k of its variables. We consider the problem of tolerant testing of k -juntas, where the testing algorithm must accept any function that is ε- close to some k -junta and reject any function that is ε′-far from every k ′-junta for some ε′ = O (ε) and k ′ = O ( k ). Our first result is an algorithm that solves this problem with query complexity polynomial in k and 1/ε. This result is obtained via a new polynomial-time approximation algorithm for submodular function minimization (SFM) under large cardinality constraints, which holds even when only given an approximate oracle access to the function. Our second result considers the case where k ′ = k . We show how to obtain a smooth tradeoff between the amount of tolerance and the query complexity in this setting. Specifically, we design an algorithm that, given ρ ∈ (0,1), accepts any function that is ε ρ/16-close to some k -junta and rejects any function that is ε-far from every k -junta. The query complexity of the algorithm is O ( k log k /ε ρ (1-ρ) k . Finally, we show how to apply the second result to the problem of tolerant isomorphism testing between two unknown Boolean functions f and g . We give an algorithm for this problem whose query complexity only depends on the (unknown) smallest k such that either f or g is close to being a k -junta.

We present a new methodology for proving distribution testing lower bounds, establishing a connection between distribution testing and the simultaneous message passing (SMP) communication model. Extending the framework of Blais, Brody, and Matulef (Computational Complexity, 2012), we show a simple way to reduce (private-coin) SMP problems to distribution testing problems. This method allows us to prove new distribution testing lower bounds, as well as to provide simple proofs of known lower bounds. Our main result is concerned with testing identity to a specific distribution p, given as a parameter. In a recent and influential work, Valiant and Valiant (FOCS, 2014) showed that the sample complexity of the aforementioned problem is closely related to the 2/3-quasinorm of p. We obtain alternative bounds on the complexity of this problem in terms of an arguably more intuitive measure and using simpler proofs. More specifically, we prove that the sample complexity is essentially determined by a fundamental operator in the theory of interpolation of Banach spaces, known as Peetre's K-functional. We show that this quantity is closely related to the size of the effective support of p (loosely speaking, the number of supported elements that constitute the vast majority of the mass of p). This result, in turn, stems from an unexpected connection to functional analysis and refined concentration of measure inequalities, which arise naturally in our reduction.

We show that for any constant \epsilon > 0 and p \ge 1, it is possible to distinguish functions f : \{0,1\}^n \to [0,1] that are submodular from those that are \epsilon-far from every submodular function in \ell_p distance with a constant number of queries. More generally, we extend the testing-by-implicit-learning framework of Diakonikolas et al.(2007) to show that every property of real-valued functions that is well-approximated in \ell_2 distance by a class of k-juntas for some k = O(1) can be tested in the \ell_p-testing model with a constant number of queries. This result, combined with a recent junta theorem of Feldman and \Vondrak (2016), yields the constant-query testability of submodularity. It also yields constant-query testing algorithms for a variety of other natural properties of valuation functions, including fractionally additive (XOS) functions, OXS functions, unit demand functions, coverage functions, and self-bounding functions.

Data visualization is an effective mechanism for identifying trends, insights, and anomalies in data. On large datasets, however, generating visualizations can take a long time, delaying the extraction of insights, hampering decision making, and reducing exploration time. One solution is to use online sampling-based schemes to generate visualizations faster while improving the displayed estimates incrementally, eventually converging to the exact visualization computed on the entire data. However, the intermediate visualizations are approximate, and often fluctuate drastically, leading to potentially incorrect decisions. We propose sampling-based incremental visualization algorithms that reveal the "salient" features of the visualization quickly---with a 46× speedup relative to baselines---while minimizing error, thus enabling rapid and error-free decision making. We demonstrate that these algorithms are optimal in terms of sample complexity, in that given the level of interactivity, they generate approximations that take as few samples as possible. We have developed the algorithms in the context of an incremental visualization tool, titled I nc V isage , for trendline and heatmap visualizations. We evaluate the usability of I nc V isage via user studies and demonstrate that users are able to make effective decisions with incrementally improving visualizations, especially compared to vanilla online-sampling based schemes.

We consider the problem of learning distributions in the presence of irrelevant features. This problem is formalized by introducing a new notion of \emphk-junta distributions. Informally, a distribution \mathcalD over the domain \mathcalX^n is a \emphk-junta distribution with respect to another distribution \mathcalU over the same domain if there is a set J ⊆[n] of size |J| \le k that captures the difference between \mathcal D and \mathcalU. We show that it is possible to learn k-junta distributions with respect to the uniform distribution over the Boolean hypercube {0,1}^n in time \poly(n^k, 1/ε). This result is obtained via a new Fourier-based learning algorithm inspired by the Low-Degree Algorithm of Linial, Mansour, and Nisan (1993). We also consider the problem of testing whether an unknown distribution is a k-junta distribution with respect to the uniform distribution. We give a nearly-optimal algorithm for this task. Both the analysis of the algorithm and the lower bound showing its optimality are obtained by establishing connections between the problem of testing junta distributions and testing uniformity of weighted collections of distributions.

Modern software systems have grown significantly in their size and complexity, therefore understanding how software systems behave when there are many configuration options, also called features, is no longer a trivial task. This is primarily due to the potentially complex interactions among the features. In this paper, we propose a novel mathematical model for performance-relevant, or quantitative in general, feature interactions, based on the theory of Boolean functions. Moreover, we provide two algorithms for detecting all such interactions with little measurement effort and potentially guaranteed accuracy and confidence level. Empirical results on real-world configurable systems demonstrated the feasibility and effectiveness of our approach.

We show that every algorithm for testing n-variate Boolean functions for monotonicityhas query complexity Ω(n1/4). All previous lower bounds for this problem were designed for non-adaptive algorithms and, as a result, the best previous lower bound for general (possibly adaptive) monotonicity testers was only Ω(logn). Combined with the query complexity of the non-adaptive monotonicity tester of Khot, Minzer, and Safra (FOCS 2015), our lower bound shows that adaptivity can result in at most a quadratic reduction in the query complexity for testing monotonicity.

Monotone Boolean functions, and the monotone Boolean circuits that compute them, have been intensively studied in complexity theory. In this paper we study the structure of Boolean functions in terms of the minimum number of negations in any circuit computing them, a complexity measure that interpolates between monotone functions and the class of all functions. We study this generalization of monotonicity from the vantage point of learning theory, establishing nearly matching upper and lower bounds on the uniform-distribution learnability of circuits in terms of the number of negations they contain. Our upper bounds are based on a new structural characterization of negation-limited circuits that extends a classical result of A.A. Markov. Our lower bounds, which employ Fourier-analytic tools from hardness amplification, give new results even for circuits with no negations (i.e. monotone functions).

Understanding how performance varies across a large number of variants of a configurable software system is important for helping stakeholders to choose a desirable variant. Given a software system with n optional features, measuring all its 2npossible configurations to determine their performances is usually infeasible. Thus, various techniques have been proposed to predict software performances based on a small sample of measured configurations. We propose a novel algorithm based on Fourier transform that is able to make predictions of any configurable software system with theoretical guarantees of accuracy and confidence level specified by the user, while using minimum number of samples up to a constant factor. Empirical results on the case studies constructed from real-world configurable systems demonstrate the effectiveness of our algorithm.

Visualizations are frequently used as a means to understand trends and gather insights from datasets, but often take a long time to generate. In this paper, we focus on the problem of rapidly generating approximate visualizations while preserving crucial visual properties of interest to analysts. Our primary focus will be on sampling algorithms that preserve the visual property of ordering ; our techniques will also apply to some other visual properties. For instance, our algorithms can be used to generate an approximate visualization of a bar chart very rapidly, where the comparisons between any two bars are correct. We formally show that our sampling algorithms are generally applicable and provably optimal in theory, in that they do not take more samples than necessary to generate the visualizations with ordering guarantees. They also work well in practice, correctly ordering output groups while taking orders of magnitude fewer samples and much less time than conventional sampling schemes.

We study the complexity of approximating Boolean functions with disjunctive normal forms (DNFs) and other depth-2 circuits, exploring two main directions: universal bounds on the approximability of all Boolean functions, and the approximability of the parity function. In the first direction, our main positive results are the first nontrivial universal upper bounds on approximability by DNFs: (a) every Boolean function can be $\epsilon$-approximated by a DNF of size $O_\epsilon(2^n/\log n)$, and (b) every Boolean function can be $\epsilon$-approximated by a DNF of width $c_\epsilon\, n$, where $c_\epsilon < 1$. Our techniques extend broadly to give strong universal upper bounds on approximability by various depth-2 circuits that generalize DNFs, including the intersection of halfspaces, low-degree Polynomial threshold functions, and unate functions. We show that the parameters of our constructions almost match the information-theoretic inapproximability of a random function. In the second direction our main positive result is the construction of an explicit DNF that approximates the following parity function: ${\sf PAR}_n$ can be $\epsilon$-approximated by a DNF of size $2^{(1-2\epsilon)n}$ and width $(1-2\epsilon)n$. Using Fourier analytic tools we show that our construction is essentially optimal not just within the class of DNFs but also within the far more expressive classes of the intersection of halfspaces and intersection of unate functions.

Given a Boolean function $f$, the $f$-isomorphism testing problem requires a randomized algorithm to distinguish functions that are identical to $f$ up to relabeling of the input variables from functions that are far from being so. An important open question in property testing is to determine for which functions $f$ we can test $f$-isomorphism with a constant number of queries. Despite much recent attention to this question, essentially only two classes of functions were known to be efficiently isomorphism testable: symmetric functions and juntas. We unify and extend these results by showing that all partially symmetric functions---functions invariant to the reordering of all but a constant number of their variables---are efficiently isomorphism testable. This class of functions, first introduced by Shannon, includes symmetric functions, juntas, and many other functions as well. We conjecture that these functions are essentially the only functions efficiently isomorphism-testable. To prove our main result, we also show that partial symmetry is efficiently testable. In turn, to prove this result we had to revisit the junta testing problem. We provide a new proof of correctness of the nearly optimal junta tester. Our new proof replaces the Fourier machinery of the original proof with a purely combinatorial argument that exploits the connection between sets of variables with low influence and intersecting families. Another important ingredient in our proofs is a new notion of symmetric influence. We use this measure of influence to prove that partial symmetry is efficiently testable and also to construct an efficient sample extractor for partially symmetric functions. We then combine the sample extractor with the testing-by-implicit-learning approach to complete the proof that partially symmetric functions are efficiently isomorphism testable.

The Hamming distance function Ham_{n,d} returns 1 on all pairs of inputs x and y that differ in at most d coordinates and returns 0 otherwise. We initiate the study of the information complexity of the Hamming distance function. We give a new optimal lower bound for the information complexity of the Ham_{n,d} function in the small-error regime where the protocol is required to err with probability at most epsilon < d/n. We also give a new conditional lower bound for the information complexity of Ham_{n,d} that is optimal in all regimes. These results imply the first new lower bounds on the communication complexity of the Hamming distance function for the shared randomness two-way communication model since Pang and El-Gamal (1986). These results also imply new lower bounds in the areas of property testing and parity decision tree complexity.

We show how the communication complexity method introduced in (Blais, Brody, Matulef 2012) can be used to prove lower bounds on the number of queries required to test properties of functions with non-hypercube domains. We use this method to prove strong, and in many cases optimal, lower bounds on the query complexity of testing fundamental properties of functions f : {1, . . ., n}d→ ℝ over hypergrid domains: monotonicity, the Lipschitz property, separate convexity, convexity and monotonicity of higher-order derivatives. There is a long line of work on upper bounds and lower bounds for many of these properties that uses a diverse set of combinatorial techniques. Our method provides a unified treatment of lower bounds for all these properties based on Fourier analysis. A key ingredient in our new lower bounds is a set of Walsh functions, a canonical Fourier basis for the set of functions on the line {1, . . ., n}. The orthogonality of the Walsh functions lets us use a product construction to extend our method from properties of functions over the line to properties of functions over hypergrids. Our product construction applies to properties over hypergrids that can be expressed in terms of axis-parallel directional derivatives, such as monotonicity, the Lipschitz property and separate convexity. We illustrate the robustness of our method by making it work for convexity, which is the property of the Hessian matrix of second derivatives being positive semidefinite and thus cannot be described by axis-parallel directional derivatives alone. Such robustness contrasts with the state of the art in the upper bounds for testing properties over hypergrids: methods that work for other properties are not applicable for testing convexity, for which no nontrivial upper bounds are known for d ≥ 2.

We study the complexity of approximating Boolean functions with DNFs and other depth-2 circuits, exploring two main directions: universal bounds on the approximability of all Boolean functions, and the approximability of the parity function. In the first direction, our main positive results are the first non-trivial universal upper bounds on appropriability by DNFs: : Every Boolean function can be ε-approximated by a DNF of size Oε(2n/ log n). : Every Boolean function can be ε-approximated by a DNF of width cεn, where cεncan be ε-approximated by a DNF of size 2(1-2ε)nand width (1 - 2ε)n. Using Fourier analytic tools we show that our construction is essentially optimal not just within the class of DNFs, but also within the far more expressive classes of the intersection of halfspaces and intersection of unate functions.

We study the problem of testing isomorphism (equivalence up to relabeling of the input variables) between Boolean functions. We prove the following: (1) For most functions $f:\{0,1\}^n \to \{0,1\}$, the query complexity of testing isomorphism to $f$ is $\Omega(n)$. Moreover, the query complexity of testing isomorphism to most $k$-juntas $f:\{0,1\}^n \to \{0,1\}$ is $\Omega(k)$. (2) Isomorphism to any $k$-junta $f:\{0,1\}^n \to \{0,1\}$ can be tested with $O(k \log k)$ queries. (3) For some $k$-juntas $f:\{0,1\}^n \to \{0,1\}$, testing isomorphism to $f$ with one-sided error requires $\Omega(k\log(n/k))$ queries. In particular, testing whether $f:\{0,1\}^n \to \{0,1\}$ is a $k$-parity with one-sided error requires $\Omega(k\log(n/k))$ queries. (4) The query complexity of testing isomorphism between two unknown functions $f,g:\{0,1\}^n \to \{0,1\}$ is $\widetilde{\Theta}(2^{n/2})$. These bounds are tight up to logarithmic factors, and they significantly strengthen the bounds proved by Fischer, Kindler, Ron, Safra, and Samorodnitsky [J. Comput. System Sci., 68 (2004), pp. 753--787] and Blais and O'Donnell [Proceedings of the IEEE Conference on Computational Complexity, 2010, pp. 235--246]. We also obtain results closely related to isomorphism testing, answering a question posed by Diakonikolas, Lee, Matulef, Onak, Rubinfeld, Servedio, and Wan [Proceedings of the IEEE Symposium on Foundations of Computer Science, 2007, pp. 549--558]: testing whether a function $f:\{0,1\}^n \to \{0,1\}$ can be computed by a circuit of size $\le s$ requires $s^{\Omega(1)}$ queries. All of our lower bounds apply to general (adaptive) testers.

One motivation for property testing of boolean functions is the idea that testing can provide a fast preprocessing step before learning. However, in most machine learning applications, it is not possible to request for labels of arbitrary examples constructed by an algorithm. Instead, the dominant query paradigm in applied machine learning, called active learning, is one where the algorithm may query for labels, but only on points in a given (polynomial-sized) unlabeled sample, drawn from some underlying distribution D. In this work, we bring this well-studied model to the domain of testing. We develop both general results for this active testing model as well as efficient testing algorithms for several important properties for learning, demonstrating that testing can still yield substantial benefits in this restricted setting. For example, we show that testing unions of d intervals can be done with O(1) label requests in our setting, whereas it is known to √ require Ω(d) labeled examples for learning (and Ω(√d) for passive testing [22] where the algorithm must pay for every example drawn from D). In fact, our results for testing unions of intervals also yield improvements on prior work in both the classic query model (where any point in the domain can be queried) and the passive testing model as well. For the problem of testing linear separators in Rn over the Gaussian distribution, we show that both active and passive testing can be done with O(√n) queries, substantially less than the Ω(n) needed for learning, with near-matching lower bounds. We also present a general combination result in this model for building testable properties out of others, which we then use to provide testers for a number of assumptions used in semi-supervised learning. In addition to the above results, we also develop a general notion of the testing dimension of a given property with respect to a given distribution, that we show characterizes (up to constant factors) the intrinsic number of label requests needed to test that property. We develop such notions for both the active and passive testing models. We then use these dimensions to prove a number of lower bounds, including for linear separators and the class of dictator functions.

Given a Boolean function f, the f-isomorphism testing problem requires a randomized algorithm to distinguish functions that are identical to f up to relabeling of the input variables from functions that are far from being so. An important open question in property testing is to determine for which functions f we can test f-isomorphism with a constant number of queries. Despite much recent attention to this question, essentially only two classes of functions were known to be efficiently isomorphism testable: symmetric functions and juntas. We unify and extend these results by showing that all partially symmetric functions -- functions invariant to the reordering of all but a constant number of their variables -- are efficiently isomorphism-testable. This class of functions, first introduced by Shannon, includes symmetric functions, juntas, and many other functions as well. We conjecture that these functions are essentially the only functions efficiently isomorphism-testable. To prove our main result, we also show that partial symmetry is efficiently testable. In turn, to prove this result we had to revisit the junta testing problem. We provide a new proof of correctness of the nearly-optimal junta tester. Our new proof replaces the Fourier machinery of the original proof with a purely combinatorial argument that exploits the connection between sets of variables with low influence and intersecting families. Another important ingredient in our proofs is a new notion of symmetric influence. We use this measure of influence to prove that partial symmetry is efficiently testable and also to construct an efficient sample extractor for partially symmetric functions. We then combine the sample extractor with the testing-by-implicit-learning approach to complete the proof that partially symmetric functions are efficiently isomorphism-testable.

We develop a new technique for proving lower bounds in property testing, by showing a strong connection between testing and communication complexity. We give a simple scheme for reducing communication problems to testing problems, thus allowing us to use known lower bounds in communication complexity to prove lower bounds in testing. This scheme is general and implies a number of new testing bounds, as well as simpler proofs of several known bounds. For the problem of testing whether a boolean function is k-linear (a parity function on k variables), we achieve a lower bound of Ω(k) queries, even for adaptive algorithms with two-sided error, thus confirming a conjecture of Goldreich (2010). The same argument behind this lower bound also implies a new proof of known lower bounds for testing related classes such as k-juntas. For some classes, such as the class of monotone functions and the class of s-sparse GF(2) polynomials, we significantly strengthen the best known bounds.

We prove new lower bounds in the area of property testing of boolean functions. Specifically, we study the problem of testing whether a boolean function f is isomorphic to a fixed function g (i.e., is equal to g up to permutation of the input variables). The analogous problem for testing graphs was solved by Fischer in 2005. The setting of boolean functions, however, appears to be more difficult, and no progress has been made since the initial study of the problem by Fischer et al. in 2004. Our first result shows that any non-adaptive algorithm for testing isomorphism to a function that "strongly" depends on k variables requires log k - O(1) queries (assuming k/n is bounded away from 1). This lower bound affirms and strengthens a conjecture appearing in the 2004 work of Fischer et al. Its proof relies on total variation bounds between hypergeometric distributions which may be of independent interest. Our second result concerns the simplest interesting case not covered by our first result: non-adaptively testing isomorphism to the Majority function on k variables. Here we show that Ω(k1/12) queries are necessary (again assuming k/n is bounded away from 1). The proof of this result relies on recently developed multidimensional invariance principle tools.

A function on n variables is called a k-junta if it depends on at most k of its variables. In this article, we show that it is possible to test whether a function is a k-junta or is "far" from being a k-junta with O(kε + k log k ) queries, where epsilon is the approximation parameter. This result improves on the previous best upper bound of O (k3/2)ε queries and is asymptotically optimal, up to a logarithmic factor.