We study the problem of crowdsourced PAC learning of threshold functions. This is a challenging problem and only recently have query-efficient algorithms been established under the assumption that a noticeable fraction of the workers are perfect. In this work, we investigate a more challenging case where the majority may behave adversarially and the rest behave as the Massart noise – a significant generalization of the perfectness assumption. We show that under the semi-verified model of Charikar et al. (2017), where we have (limited) access to a trusted oracle who always returns correct annotations, it is possible to PAC learn the underlying hypothesis class with a manageable amount of label queries. Moreover, we show that the labeling cost can be drastically mitigated via the more easily obtained comparison queries. Orthogonal to recent developments in semi-verified or list-decodable learning that crucially rely on data distributional assumptions, our PAC guarantee holds by exploring the wisdom of the crowd.

The concept class of low-degree polynomial threshold functions (PTFs) plays a fundamental role in machine learning. In this paper, we study PAC learning of $K$-sparse degree-$d$ PTFs on $\mathbb{R}^n$, where any such concept depends only on $K$ out of $n$ attributes of the input. Our main contribution is a new algorithm that runs in time $({nd}/{\epsilon})^{O(d)}$ and under the Gaussian marginal distribution, PAC learns the class up to error rate $\epsilon$ with $O(\frac{K^{4d}}{\epsilon^{2d}} \cdot \log^{5d} n)$ samples even when an $\eta \leq O(\epsilon^d)$ fraction of them are corrupted by the nasty noise of Bshouty et al. (2002), possibly the strongest corruption model. Prior to this work, attribute-efficient robust algorithms are established only for the special case of sparse homogeneous halfspaces. Our key ingredients are: 1) a structural result that translates the attribute sparsity to a sparsity pattern of the Chow vector under the basis of Hermite polynomials, and 2) a novel attribute-efficient robust Chow vector estimation algorithm which uses exclusively a restricted Frobenius norm to either certify a good approximation or to validate a sparsity-induced degree-$2d$ polynomial as a filter to detect corrupted samples.

The emergence of evolving data privacy policies and regulations has sparked a growing interest in the concept of "machine unlearning", which involves enabling machine learning models to forget specific data instances. In this paper, we specifically focus on edge unlearning in Graph Neural Networks (GNNs), which entails training a new GNN model as if certain specified edges never existed in the original training graph. Unlike conventional unlearning scenarios where data samples are treated as independent entities, edges in graphs exhibit correlation. Failing to carefully account for this data dependency would result in the incomplete removal of the requested data from the model. While retraining the model from scratch by excluding the specific edges can eliminate their influence, this approach incurs a high computational cost. To overcome this challenge, we introduce CEU, a Certified Edge Unlearning framework. CEU expedites the unlearning process by updating the parameters of the pre-trained GNN model in a single step, ensuring that the update removes the influence of the removed edges from the model. We formally prove that CEU offers a rigorous theoretical guarantee under the assumption of convexity on the loss function. Our empirical analysis further demonstrates the effectiveness and efficiency of CEU for both linear and deep GNNs - it achieves significant speedup gains compared to retraining and existing unlearning methods while maintaining comparable model accuracy to retraining from scratch.

Active learning has become a prevalent technique for designing label-efficient algorithms, where the central principle is to only query and fit “informative” labeled instances. It is, however, known that an active learning algorithm may incur unfairness due to such instance selection procedure. In this paper, we henceforth study metric-fair active learning of homogeneous halfspaces, and show that under the distribution-dependent PAC learning model, fairness and label efficiency can be achieved simultaneously. We further propose two extensions of our main results: 1) we show that it is possible to make the algorithm robust to the adversarial noise – one of the most challenging noise models in learning theory; and 2) it is possible to significantly improve the label complexity when the underlying halfspace is sparse.

We study crowdsourced PAC learning of threshold function, where the labels are gathered from a pool of annotators some of whom may behave adversarially. This is yet a challenging problem and until recently has computationally and query efficient PAC learning algorithm been established by Awasthi et al. (2017). In this paper, we show that by leveraging the more easily acquired pairwise comparison queries, it is possible to exponentially reduce the label complexity while retaining the overall query complexity and runtime. Our main algorithmic contributions are a comparison-equipped labeling scheme that can faithfully recover the true labels of a small set of instances, and a label-efficient filtering process that in conjunction with the small labeled set can reliably infer the true labels of a large instance set.

Outlier-robust principal component analysis (ORPCA) has been broadly applied in scientific discovery in the last decades. In this paper, we study online ORPCA, an important variant that addresses the practical challenge that the data points arrive in a sequential manner and the goal is to recover the underlying subspace of the clean data with one pass of the data. Our main contribution is the first provable algorithm that enjoys comparable recovery guarantee to the best known batch algorithm, while significantly improving upon the state-of-the-art online ORPCA algorithms. The core technique is a robust version of the residual norm which, informally speaking, leverages not only the importance of a data point, but also how likely it behaves as an outlier.

Robust mean estimation is one of the most important problems in statistics: given a set of samples in $\mathbb{R}^d$ where an $\alpha$ fraction are drawn from some distribution $D$ and the rest are adversarially corrupted, we aim to estimate the mean of $D$. A surge of recent research interest has been focusing on the list-decodable setting where $\alpha \in (0, \frac12]$, and the goal is to output a finite number of estimates among which at least one approximates the target mean. In this paper, we consider that the underlying distribution $D$ is Gaussian with $k$-sparse mean. Our main contribution is the first polynomial-time algorithm that enjoys sample complexity $O\big(\mathrm{poly}(k, \log d)\big)$, i.e. poly-logarithmic in the dimension. One of our core algorithmic ingredients is using low-degree {\em sparse polynomials} to filter outliers, which may find more applications.

This paper is concerned with computationally efficient learning of homogeneous sparse halfspaces in $\mathbb{R}^d$ under noise. Though recent works have established attribute-efficient learning algorithms under various types of label noise (e.g. bounded noise), it remains an open question of when and how $s$-sparse halfspaces can be efficiently learned under the challenging {\em malicious noise} model, where an adversary may corrupt both the unlabeled examples and the labels. We answer this question in the affirmative by designing a computationally efficient active learning algorithm with near-optimal label complexity of $\tilde{O}(s \log^4\frac{d}{\epsilon})$ and noise tolerance $\eta = \Omega(\epsilon)$, where $\epsilon \in (0, 1)$ is the target error rate, under the assumption that the distribution over (uncorrupted) unlabeled examples is isotropic log-concave. Our algorithm can be straightforwardly tailored to the passive learning setting, and we show that the sample complexity is $\tilde{O}(\frac{1}{\epsilon}s^2 \log^5 d)$ which also enjoys attribute efficiency. Our main techniques include attribute-efficient paradigms for soft outlier removal and for empirical risk minimization, and a new analysis of uniform concentration for unbounded instances – all of them crucially take the sparsity structure of the underlying halfspace into account.

We study {\em online} active learning of homogeneous halfspaces in $\mathbb{R}^d$ with adversarial noise where the overall probability of a noisy label is constrained to be at most $\nu$. Our main contribution is a Perceptron-like online active learning algorithm that runs in polynomial time, and under the conditions that the marginal distribution is isotropic log-concave and $\nu = \Omega(\epsilon)$, where $\epsilon \in (0, 1)$ is the target error rate, our algorithm PAC learns the underlying halfspace with near-optimal label complexity of $\tilde{O}\big(d \cdot \polylog(\frac{1}{\epsilon})\big)$ and sample complexity of $\tilde{O}\big(\frac{d}{\epsilon} \big)$. Prior to this work, existing online algorithms designed for tolerating the adversarial noise are subject to either label complexity polynomial in $\frac{1}{\epsilon}$, or suboptimal noise tolerance, or restrictive marginal distributions. With the additional prior knowledge that the underlying halfspace is $s$-sparse, we obtain attribute-efficient label complexity of $\tilde{O}\big( s \cdot \polylog(d, \frac{1}{\epsilon}) \big)$ and sample complexity of $\tilde{O}\big(\frac{s}{\epsilon} \cdot \polylog(d) \big)$. As an immediate corollary, we show that under the agnostic model where no assumption is made on the noise rate $\nu$, our active learner achieves an error rate of $O(OPT) + \epsilon$ with the same running time and label and sample complexity, where $OPT$ is the best possible error rate achievable by any homogeneous halfspace.

We study efficient PAC learning of homogeneous halfspaces in $\mathbb{R}^d$ in the presence of malicious noise of Valiant (1985). This is a challenging noise model and only until recently has near-optimal noise tolerance bound been established under the mild condition that the unlabeled data distribution is isotropic log-concave. However, it remains unsettled how to obtain the optimal sample complexity simultaneously. In this work, we present a new analysis for the algorithm of Awasthi et al. (2017) and show that it essentially achieves the near-optimal sample complexity bound of $\tilde{O}(d)$, improving the best known result of $\tilde{O}(d^2)$. Our main ingredient is a novel incorporation of a matrix Chernoff-type inequality to bound the spectrum of an empirical covariance matrix for well-behaved distributions, in conjunction with a careful exploration of the localization schemes of Awasthi et al. (2017). We further extend the algorithm and analysis to the more general and stronger nasty noise model of Bshouty et al. (2002), showing that it is still possible to achieve near-optimal noise tolerance and sample complexity in polynomial time.

We study active learning of homogeneous $s$-sparse halfspaces in $\mathbb{R}^d$ under the setting where the unlabeled data distribution is isotropic log-concave and each label is flipped with probability at most $\eta$ for a parameter $\eta \in \big[0, \frac12\big)$, known as the bounded noise. Even in the presence of mild label noise, i.e. $\eta$ is a small constant, this is a challenging problem and only recently have label complexity bounds of the form $\tilde{O}(s \cdot polylog(d, \frac{1}{\epsilon}))$ been established in [Zhang 2018] for computationally efficient algorithms. In contrast, under high levels of label noise, the label complexity bounds achieved by computationally efficient algorithms are much worse: the best known result [Awasthi et al. 2016] provides a computationally efficient algorithm with label complexity $\tilde{O}((s ln d/\epsilon)^{poly(1/(1-2\eta))})$, which is label-efficient only when the noise rate $\eta$ is a fixed constant. In this work, we substantially improve on it by designing a polynomial time algorithm for active learning of $s$-sparse halfspaces, with a label complexity of $\tilde{O}\big(\frac{s}{(1-2\eta)^4} polylog (d, \frac 1 \epsilon) \big)$. This is the first efficient algorithm with label complexity polynomial in $\frac{1}{1-2\eta}$ in this setting, which is label-efficient even for $\eta$ arbitrarily close to $\frac12$. Our active learning algorithm and its theoretical guarantees also immediately translate to new state-of-the-art label and sample complexity results for full-dimensional active and passive halfspace learning under arbitrary bounded noise.

This paper concerns the problem of 1-bit compressed sensing, where the goal is to estimate a sparse signal from a few of its binary measurements. We study a non-convex sparsity-constrained program and present a novel and concise analysis that moves away from the widely used notion of Gaussian width. We show that with high probability a simple algorithm is guaranteed to produce an accurate approximation to the normalized signal of interest under the L2-metric. On top of that, we establish an ensemble of new results that address norm estimation, support recovery, and model misspecification. On the computational side, it is shown that the non-convex program can be solved via one-step hard thresholding which is dramatically efficient in terms of time complexity and memory footprint. On the statistical side, it is shown that our estimator enjoys a near-optimal error rate under standard conditions. The theoretical results are further substantiated by numerical experiments.

1-bit matrix completion refers to the problem of recovering a real-valued low-rank matrix from a small fraction of its sign patterns. In many real-world applications, however, the observations are not only highly quantized, but also grossly corrupted. In this work, we consider the noisy statistical model where each observed entry can be flipped with some probability after quantization. We propose a simple maximum likelihood estimator which is shown to be robust to the sign flipping noise. In particular, we prove an upper bound on the statistical error, showing that with overwhelming probability $n = O(poly(1-2E[\tau])^{-2} rd \log d)$ samples are sufficient for accurate recovery, where $r$ and $d$ are the rank and dimension of the underlying matrix respectively, and tau in $[0, 1/2)$ is a random variable that parameterizes the sign flipping noise. Furthermore, a lower bound is established showing that the obtained sample complexity is near-optimal for prevalent statistical models. Finally, we substantiate our theoretical findings with a comprehensive study on synthetic and realistic data sets, and demonstrate the state-of-the-art performance.

In large-scale machine learning applications and high-dimensional statistics, it is ubiquitous to address a considerable number of features among which many are redundant. As a remedy, online feature selection has attracted increasing attention in recent years. It sequentially reveals features and evaluates the importance of them. Though online feature selection has proven an elegant methodology, it is usually challenging to carry out a rigorous theoretical characterization. In this work, we propose a provable online feature selection algorithm that utilizes the online leverage score. The selected features are then fed to $k$-means clustering, making the clustering step memory and computationally efficient. We prove that with high probability, performing $k$-means clustering based on the selected feature space does not deviate far from the optimal clustering using the original data. The empirical results on real-world data sets demonstrate the effectiveness of our algorithm.

Recovering the support of a sparse signal from its compressed samples has been one of the most important problems in high dimensional statistics. In this paper, we present a novel analysis for the hard thresholding pursuit (HTP) algorithm, showing that it exactly recovers the support of an arbitrary s-sparse signal within O(sklogk) iterations via a properly chosen proxy function, where k is the condition number of the problem. In stark contrast to the theoretical results in the literature, the iteration complexity we obtained holds without assuming the restricted isometry property, or relaxing the sparsity, or utilizing the optimality of the underlying signal. We further extend our result to a more challenging scenario, where the subproblem involved in HTP cannot be solved exactly. We prove that even in this setting, support recovery is possible and the computational complexity of HTP is established. Numerical study substantiates our theoretical results.

In machine learning and compressed sensing, it is of central importance to understand when a tractable algorithm recovers the support of a sparse signal from its compressed measurements. In this paper, we present a principled analysis on the support recovery performance for a family of hard thresholding algorithms. To this end, we appeal to the partial hard thresholding (PHT) operator proposed recently by Jain et al. [IEEE Trans. Information Theory, 2017]. We show that under proper conditions, PHT recovers an arbitrary "s"-sparse signal within O(s kappa log kappa) iterations where "kappa" is an appropriate condition number. Specifying the PHT operator, we obtain the best known result for hard thresholding pursuit and orthogonal matching pursuit with replacement. Experiments on the simulated data complement our theoretical findings and also illustrate the effectiveness of PHT compared to other popular recovery methods.

This work studies the binary matrix completion problem underlying a large body of real-world applications such as signed link prediction and information propagation. That is, each entry of the matrix indicates a binary preference such as "like" or "dislike", "trust" or "distrust". However, the performance of existing matrix completion methods may be hindered owing to three practical challenges: 1) the observed data are with binary label (i.e., not real value); 2) the data are typically sampled non-uniformly (i.e., positive links dominate the negative ones) and 3) a network may have a huge volume of data (i.e., memory and computational issue).

A vast body of recent works in the literature has shown that exploring structures beyond data low-rankness can boost the performance of subspace clustering methods such as Low-Rank Representation (LRR). It has also been well recognized that the matrix factorization framework might offer more flexibility on pursuing underlying structures of the data. In this paper, we propose to learn structured LRR by factorizing the nuclear norm regularized matrix, which leads to our proposed non-convex formulation NLRR. Interestingly, this formulation of NLRR provides a general framework for unifying a variety of popular algorithms including LRR, dictionary learning, robust principal component analysis, sparse subspace clustering, etc. Several variants of NLRR are also proposed, for example, to promote sparsity while preserving low-rankness. We design a practical algorithm for NLRR and its variants, and establish theoretical guarantee for the stability of the solution and the convergence of the algorithm. Perhaps surprisingly, the computational and memory cost of NLRR can be reduced by roughly one order of magnitude compared to the cost of LRR. Experiments on extensive simulations and real datasets confirm the robustness of efficiency of NLRR and the variants.

Low-Rank Representation (LRR) has been a significant method for segmenting data that are generated from a union of subspaces. It is also known that solving LRR is challenging in terms of time complexity and memory footprint, in that the size of the nuclear norm regularized matrix is n-by-n (where n is the number of samples). In this paper, we thereby develop a novel online implementation of LRR that reduces the memory cost from O(n^2) to O(pd), with p being the ambient dimension and d being some estimated rank (d < p < n). We also establish the theoretical guarantee that the sequence of solutions produced by our algorithm converges to a stationary point of the expected loss function asymptotically. Extensive experiments on synthetic and realistic datasets further substantiate that our algorithm is fast, robust and memory efficient.

In this paper, we utilize structured learning to simultaneously address two intertwined problems: 1) human pose estimation (HPE) and 2) garment attribute classification (GAC), which are valuable for a variety of computer vision and multimedia applications. Unlike previous works that usually handle the two problems separately, our approach aims to produce an optimal joint estimation for both HPE and GAC via a unified inference procedure. To this end, we adopt a preprocessing step to detect potential human parts from each image (i.e., a set of candidates) that allows us to have a manageable input space. In this way, the simultaneous inference of HPE and GAC is converted to a structured learning problem, where the inputs are the collections of candidate ensembles, outputs are the joint labels of human parts and garment attributes, and joint feature representation involves various cues such as pose-specific features, garment-specific features, and cross-task features that encode correlations between human parts and garment attributes. Furthermore, we explore the strong edge evidence around the potential human parts so as to derive more powerful representations for oriented human parts. Such evidences can be seamlessly integrated into our structured learning model as a kind of energy function, and the learning process could be performed by standard structured support vector machines algorithm. However, the joint structure of the two problems is a cyclic graph, which hinders efficient inference. To resolve this issue, we compute instead approximate optima using an iterative procedure, where in each iteration, the variables of one problem are fixed. In this way, satisfactory solutions can be efficiently computed by dynamic programming. Experimental results on two benchmark data sets show the state-of-the-art performance of our approach.