arXiv subjects

Arsen Vasilyan

Publications and source records attributed to Arsen Vasilyan.

25 records · Page 2Linked to original sources

arXiv2023

Agnostic proper learning of monotone functions: beyond the black-box correction barrier

We give the first agnostic, efficient, proper learning algorithm for monotone Boolean functions. Given $2^{\tilde{O}(\sqrt{n}/\varepsilon)}$ uniformly random examples of an unknown function $f:\{\pm 1\}^n \rightarrow \{\pm 1\}$, our algorithm outputs a hypothesis $g:\{\pm 1\}^n \rightarrow \{\pm 1\}$ that is monotone and $(\mathrm{opt} + \varepsilon)$-close to $f$, where $\mathrm{opt}$ is the distance from $f$ to the closest monotone function. The running time of the algorithm (and consequently the size and evaluation time of the hypothesis) is also $2^{\tilde{O}(\sqrt{n}/\varepsilon)}$, nearly matching the lower bound of Blais et al (RANDOM '15). We also give an algorithm for estimating up to additive error $\varepsilon$ the distance of an unknown function $f$ to monotone using a run-time of $2^{\tilde{O}(\sqrt{n}/\varepsilon)}$. Previously, for both of these problems, sample-efficient algorithms were known, but these algorithms were not run-time efficient. Our work thus closes this gap in our knowledge between the run-time and sample complexity. This work builds upon the improper learning algorithm of Bshouty and Tamon (JACM '96) and the proper semiagnostic learning algorithm of Lange, Rubinfeld, and Vasilyan (FOCS '22), which obtains a non-monotone Boolean-valued hypothesis, then ``corrects'' it to monotone using query-efficient local computation algorithms on graphs. This black-box correction approach can achieve no error better than $2\mathrm{opt} + \varepsilon$ information-theoretically; we bypass this barrier by a) augmenting the improper learner with a convex optimization step, and b) learning and correcting a real-valued function before rounding its values to Boolean. Our real-valued correction algorithm solves the ``poset sorting'' problem of [LRV22] for functions over general posets with non-Boolean labels.

cs.DS↗

arXiv2023

Tester-Learners for Halfspaces: Universal Algorithms

We give the first tester-learner for halfspaces that succeeds universally over a wide class of structured distributions. Our universal tester-learner runs in fully polynomial time and has the following guarantee: the learner achieves error $O(\mathrm{opt}) + ε$ on any labeled distribution that the tester accepts, and moreover, the tester accepts whenever the marginal is any distribution that satisfies a Poincaré inequality. In contrast to prior work on testable learning, our tester is not tailored to any single target distribution but rather succeeds for an entire target class of distributions. The class of Poincaré distributions includes all strongly log-concave distributions, and, assuming the Kannan--Lóvasz--Simonovits (KLS) conjecture, includes all log-concave distributions. In the special case where the label noise is known to be Massart, our tester-learner achieves error $\mathrm{opt} + ε$ while accepting all log-concave distributions unconditionally (without assuming KLS). Our tests rely on checking hypercontractivity of the unknown distribution using a sum-of-squares (SOS) program, and crucially make use of the fact that Poincaré distributions are certifiably hypercontractive in the SOS framework.

cs.LG↗

arXiv2023

Properly learning monotone functions via local reconstruction

We give a $2^{\tilde{O}(\sqrt{n}/ε)}$-time algorithm for properly learning monotone Boolean functions under the uniform distribution over $\{0,1\}^n$. Our algorithm is robust to adversarial label noise and has a running time nearly matching that of the state-of-the-art improper learning algorithm of Bshouty and Tamon (JACM '96) and an information-theoretic lower bound of Blais et al (RANDOM '15). Prior to this work, no proper learning algorithm with running time smaller than $2^{Ω(n)}$ was known to exist. The core of our proper learner is a \emph{local computation algorithm} for sorting binary labels on a poset. Our algorithm is built on a body of work on distributed greedy graph algorithms; specifically we rely on a recent work of Ghaffari (FOCS'22), which gives an efficient algorithm for computing maximal matchings in a graph in the LCA model of Rubinfeld et al and Alon et al (ICS'11, SODA'12). The applications of our local sorting algorithm extend beyond learning on the Boolean cube: we also give a tolerant tester for Boolean functions over general posets that distinguishes functions that are $ε/3$-close to monotone from those that are $ε$-far. Previous tolerant testers for the Boolean cube only distinguished between $ε/Ω(\sqrt{n})$-close and $ε$-far.

cs.DS↗

arXiv2023

An Efficient Tester-Learner for Halfspaces

We give the first efficient algorithm for learning halfspaces in the testable learning model recently defined by Rubinfeld and Vasilyan (2023). In this model, a learner certifies that the accuracy of its output hypothesis is near optimal whenever the training set passes an associated test, and training sets drawn from some target distribution -- e.g., the Gaussian -- must pass the test. This model is more challenging than distribution-specific agnostic or Massart noise models where the learner is allowed to fail arbitrarily if the distributional assumption does not hold. We consider the setting where the target distribution is Gaussian (or more generally any strongly log-concave distribution) in $d$ dimensions and the noise model is either Massart or adversarial (agnostic). For Massart noise, our tester-learner runs in polynomial time and outputs a hypothesis with (information-theoretically optimal) error $\mathsf{opt} + ε$ for any strongly log-concave target distribution. For adversarial noise, our tester-learner obtains error $O(\mathsf{opt}) + ε$ in polynomial time when the target distribution is Gaussian; for strongly log-concave distributions, we obtain $\tilde{O}(\mathsf{opt}) + ε$ in quasipolynomial time. Prior work on testable learning ignores the labels in the training set and checks that the empirical moments of the covariates are close to the moments of the base distribution. Here we develop new tests of independent interest that make critical use of the labels and combine them with the moment-matching approach of Gollakota et al. (2023). This enables us to simulate a variant of the algorithm of Diakonikolas et al. (2020) for learning noisy halfspaces using nonconvex SGD but in the testable learning setting.

cs.LG↗

arXiv2022

Testing distributional assumptions of learning algorithms

There are many high dimensional function classes that have fast agnostic learning algorithms when assumptions on the distribution of examples can be made, such as Gaussianity or uniformity over the domain. But how can one be confident that data indeed satisfies such assumption, so that one can trust in output quality of the agnostic learning algorithm? We propose a model by which to systematically study the design of tester-learner pairs $(\mathcal{A},\mathcal{T})$, such that if the distribution on examples in the data passes the tester $\mathcal{T}$ then one can safely trust the output of the agnostic learner $\mathcal{A}$ on the data. To demonstrate the power of the model, we apply it to the classical problem of agnostically learning halfspaces under the standard Gaussian distribution and present a tester-learner pair with combined run-time of $n^{\tilde{O}(1/ε^4)}$. This qualitatively matches that of the best known ordinary agnostic learning algorithms for this task. In contrast, finite sample Gaussianity testers do not exist for the $L_1$ and EMD distance measures. A key step is to show that half-spaces are well-approximated with low-degree polynomials relative to distributions with low-degree moments close to those of a Gaussian. We also go beyond spherically-symmetric distributions, and give a tester-learner pair for halfspaces under the uniform distribution on $\{0,1\}^n$ with combined run-time of $n^{\tilde{O}(1/ε^4)}$. This is achieved using polynomial approximation theory and critical index machinery. We also show there exist some well-studied settings where $2^{\tilde{O}(\sqrt{n})}$ run-time agnostic learning algorithms are available, yet the combined run-times of tester-learner pairs must be as high as $2^{Ω(n)}$. On that account, the design of tester-learner pairs is a research direction in its own right independent of standard agnostic learning.

cs.LG↗

arXiv2020

Monotone probability distributions over the Boolean cube can be learned with sublinear samples

A probability distribution over the Boolean cube is monotone if flipping the value of a coordinate from zero to one can only increase the probability of an element. Given samples of an unknown monotone distribution over the Boolean cube, we give (to our knowledge) the first algorithm that learns an approximation of the distribution in statistical distance using a number of samples that is sublinear in the domain. To do this, we develop a structural lemma describing monotone probability distributions. The structural lemma has further implications to the sample complexity of basic testing tasks for analyzing monotone probability distributions over the Boolean cube: We use it to give nontrivial upper bounds on the tasks of estimating the distance of a monotone distribution to uniform and of estimating the support size of a monotone distribution. In the setting of monotone probability distributions over the Boolean cube, our algorithms are the first to have sample complexity lower than known lower bounds for the same testing tasks on arbitrary (not necessarily monotone) probability distributions. One further consequence of our learning algorithm is an improved sample complexity for the task of testing whether a distribution on the Boolean cube is monotone.

cs.DS↗

arXiv2019

Approximating the noise sensitivity of a monotone Boolean function

The noise sensitivity of a Boolean function $f: \{0,1\}^n \rightarrow \{0,1\}$ is one of its fundamental properties. A function of a positive noise parameter $δ$, it is denoted as $NS_δ[f]$. Here we study the algorithmic problem of approximating it for monotone $f$, such that $NS_δ[f] \geq 1/n^{C}$ for constant $C$, and where $δ$ satisfies $1/n \leq δ\leq 1/2$. For such $f$ and $δ$, we give a randomized algorithm performing $O\left(\frac{\min(1,\sqrt{n} δ\log^{1.5} n) }{NS_δ[f]} \text{poly}\left(\frac{1}ε\right)\right)$ queries and approximating $NS_δ[f]$ to within a multiplicative factor of $(1\pm ε)$. Given the same constraints on $f$ and $δ$, we also prove a lower bound of $Ω\left(\frac{\min(1,\sqrt{n} δ)}{NS_δ[f] \cdot n^ξ}\right)$ on the query complexity of any algorithm that approximates $NS_δ[f]$ to within any constant factor, where $ξ$ can be any positive constant. Thus, our algorithm's query complexity is close to optimal in terms of its dependence on $n$. We introduce a novel descending-ascending view of noise sensitivity, and use it as a central tool for the analysis of our algorithm. To prove lower bounds on query complexity, we develop a technique that reduces computational questions about query complexity to combinatorial questions about the existence of "thin" functions with certain properties. The existence of such "thin" functions is proved using the probabilistic method. These techniques also yield previously unknown lower bounds on the query complexity of approximating other fundamental properties of Boolean functions: the total influence and the bias.

cs.DS↗