Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs), and typically are applied independently. Applying these techniques jointly via co-optimization has the potential to produce smaller, high-quality models. However, existing joint schemes are not widely used because of (1) engineering difficulties (complicated multi-stage processes), (2) black-box optimization (extensive hyperparameter tuning to control the overall compression), and (3) insufficient architecture generalization. To address these limitations, we present the framework GETA, which automatically and efficiently performs joint structured pruning and quantization- aware training on any DNN. GETA introduces three key innovations: (i) a quantization-aware dependency graph (QADG) that constructs a pruning search space for generic quantization-aware DNN, (ii) a partially projected stochastic gradient method that guarantees layerwise bit constraints are satisfied, and (iii) a new joint learning strategy that incorporates interpretable relationships between pruning and quantization. We present numerical experiments on both convolutional neural networks and transformer architectures that show that our approach achieves competitive (often superior) performance compared to existing joint pruning and quantization methods. Source code is available at https://github.com/microsoft/GETA.

Manifold clustering is an important problem in motion and video segmentation, natural image clustering, and other applications where high-dimensional data lie on multiple, low-dimensional, nonlinear manifolds. While current state-of-the-art methods on large-scale datasets such as CIFAR provide good empirical performance, they do not have any proof of theoretical correctness. In this work, we propose a method that clusters data belonging to a union of nonlinear manifolds. Furthermore, for a given input data sample $y$ belonging to the $l$th manifold $\mathcal{M}_l$, we provide geometric conditions that guarantee a manifold-preserving representation of $y$ can be recovered from the solution to the proposed model. The geometric conditions require that (i) $\mathcal{M}_l$ is well-sampled in the neighborhood of $y$, with the sampling density given as a function of the curvature, and (ii) $\mathcal{M}_l$ is sufficiently separated from the other manifolds. In addition to providing proof of correctness in this setting, a numerical comparison with state-of-the-art methods on CIFAR datasets shows that our method performs competitively although marginally worse than methods without

This paper introduces a new proximal stochastic gradient method with variance reduction and stabilization for minimizing the sum of a convex stochastic function and a group sparsity-inducing regularization function. Since the method may be viewed as a stabilized version of the recently proposed algorithm PStorm, we call our algorithm S-PStorm. Our analysis shows that S-PStorm has strong convergence results. In particular, we prove an upper bound on the number of iterations required by S-PStorm before its iterates correctly identify (with high probability) an optimal support (i.e., the zero and nonzero structure of an optimal solution). Most algorithms in the literature with such a support identification property use variance reduction techniques that require either periodically evaluating an exact gradient or storing a history of stochastic gradients. Unlike these methods, S-PStorm achieves variance reduction without requiring either of these, which is advantageous. Moreover, our support-identification result for S-PStorm shows that, with high probability, an optimal support will be identified correctly in all iterations with index above a threshold. We believe that this type of result is new to the literature since the few existing other results prove that the optimal support is identified with high probability at each iteration with a sufficiently large index (meaning that the optimal support might be identified in some iterations, but not in others). Numerical experiments on regularized logistic loss problems show that S-PStorm outperforms existing methods in various metrics that measure how efficiently and robustly iterates of an algorithm identify an optimal support.

Finding a small set of representatives from an unlabeled dataset is a core problem in a broad range of applications such as dataset summarization and information extraction. Classical exemplar selection methods such as$k$-medoids work under the assumption that the data points are close to a few cluster centroids, and cannot handle the case where data lie close to a union of subspaces. This paper proposes a new exemplar selection model that searches for a subset that best reconstructs all data points as measured by the$\ell _1$norm of the representation coefficients. Geometrically, this subset best covers all the data points as measured by the Minkowski functional of the subset. To solve our model efficiently, we introduce a farthest first search algorithm that iteratively selects the worst represented point as an exemplar. When the dataset is drawn from a union of independent subspaces, our method is able to select sufficiently many representatives from each subspace. We further develop an exemplar based subspace clustering method that is robust to imbalanced data and efficient for large scale data. Moreover, we show that a classifier trained on the selected exemplars (when they are labeled) can correctly classify the rest of the data points.

State-of-the-art subspace clustering methods are based on convex formulations whose theoretical guarantees require the subspaces to be low-dimensional. Dual Principal Component Pursuit (DPCP) is a non-convex method that is specifically designed for learning high-dimensional subspaces, such as hyperplanes. However, existing analyses of DPCP in the multi-hyperplane case lack a precise characterization of the distribution of the data and involve quantities that are difficult to interpret. Moreover, the provable algorithm based on recursive linear programming is not efficient. In this paper, we introduce a new notion of geometric dominance, which explicitly captures the distribution of the data, and derive both geometric and probabilistic conditions under which a global solution to DPCP is a normal vector to a geometrically dominant hyperplane. We then prove that the DPCP problem for a union of hyperplanes satisfies a Riemannian regularity condition, and use this result to show that a scalable Riemannian subgradient method exhibits (local) linear convergence to the normal vector of the geometrically dominant hyperplane. Finally, we show that integrating DPCP into popular subspace clustering schemes, such as K-ensembles, leads to superior or competitive performance over the state-of-the-art in clustering hyperplanes.

The Dual Principal Component Pursuit (DPCP) method has been proposed to robustly recover a subspace of high-relative dimension from corrupted data. Existing analyses and algorithms of DPCP, however, mainly focus on finding a normal to a single hyperplane that contains the inliers. Although these algorithms can be extended to a subspace of higher co-dimension through a recursive approach that sequentially finds a new basis element of the space orthogonal to the subspace, this procedure is computationally expensive and lacks convergence guarantees. In this paper, we consider a DPCP approach for simultaneously computing the entire basis of the orthogonal complement subspace (we call this a holistic approach) by solving a non-convex non-smooth optimization problem over the Grassmannian. We provide geometric and statistical analyses for the global optimality and prove that it can tolerate as many outliers as the square of the number of inliers, under both noiseless and noisy settings. We then present a Riemannian regularity condition for the problem, which is then used to prove that a Riemannian subgradient method converges linearly to a neighborhood of the orthogonal subspace with error proportional to the noise level.

Much of the theory for classical sparse recovery is based on conditions on the dictionary that are both necessary and sufficient (e.g., nullspace property) or only sufficient (e.g., incoherence and restricted isometry). In contrast, much of the theory for subspace-preserving recovery, the theoretical underpinnings for sparse subspace classification and clustering methods, is based on conditions on the subspaces and the data that are only sufficient (e.g., subspace incoherence and data inner-radius). This paper derives a necessary and sufficient condition for subspace-preserving recovery that is inspired by the classical nullspace property.Based on this novel condition, called here the subspace nullspace property, we derive equivalent characterizations that either admit a clear geometric interpretation that relates data distribution and subspace separation to the recovery success, or can be verified using a finite set of extreme points of a properly defined set. We further exploit these characterizations to derive new sufficient conditions, based on inner-radius and outer-radius measures and dual bounds, that generalize existing conditions and preserve the geometric interpretations. These results fill an important gap in the subspace-preserving recovery literature.

Much of the existing literature in sparse recovery is concerned with the following question: given a sparsity pattern and a corresponding regularizer, derive conditions on the dictionary under which exact recovery is possible. In this paper, we study the opposite question: given a dictionary and thel1-norm regularizer, find the largest sparsity pattern that can be recovered. We show that such a pattern is described by a mathematical object called a “maximum abstract simplicial complex,” and provide two different characterizations of this object: one based on extreme points and the other based on vectors of minimal support. In addition, we show how this new framework is useful in the study of sparse recovery problems when the dictionary takes the form of a graph incidence matrix or a partial discrete Fourier transform. In case of incidence matrices, we show that the largest sparsity pattern that can be recovered is determined by the set of simple cycles of the graph. As a byproduct, we show that standard sparse recovery can be certified in polynomial time, although this is known to be NP-hard for general matrices. In the case of the partial discrete Fourier transform, our characterization of the largest sparsity pattern that can be recovered requires the unknown signal to be real and its dimension to be a prime number.

We revisit robust estimation of homographies over point correspondences between two or three views, a fundamental problem in geometric vision. The analysis serves as a platform to support a rigorous investigation of Dual Principal Component Pursuit (DPCP) as a valid and powerful alternative to RANSAC for robust model fitting in multiple-view geometry. Homography fitting is cast as a robust nullspace estimation problem over either homographic or epipolar/trifocal embeddings. We prove that the nullspace of epipolar or trifocal embeddings in the homographic scenario, of dimension 3 and 6 for two and three views respectively, is defined by unique, computable homographies. Experiments show that DPCP performs on par with USAC with local optimization, while requiring an order of magnitude less computing time, and it also outperforms a recent deep learning implementation for homography estimation.

Arguably, the two most popular accelerated or momentum-based optimization methods are Nesterov's accelerated gradient and Polyaks's heavy ball, both corresponding to different discretizations of a particular second order differential equation with a friction term. Such connections with continuous-time dynamical systems have been instrumental in demystifying acceleration phenomena in optimization. Here we study structure-preserving discretizations for a certain class of dissipative (conformal) Hamiltonian systems, allowing us to analyze the symplectic structure of both Nesterov and heavy ball, besides providing several new insights into these methods. Moreover, we propose a new algorithm based on a dissipative relativistic system that normalizes the momentum and may result in more stable/faster optimization. Importantly, such a method generalizes both Nesterov and heavy ball, each being recovered as distinct limiting cases, and has potential advantages at no additional cost.

Subspace clustering methods based on expressing each data point as a linear combination of other data points have achieved great success in computer vision applications such as motion segmentation, face and digit clustering. In face clustering, the subspaces are linear and subspace clustering methods can be applied directly. In motion segmentation, the subspaces are affine and an additional affine constraint on the coefficients is often enforced. However, since affine subspaces can always be embedded into linear subspaces of one extra dimension, it is unclear if the affine constraint is really necessary. This paper shows, both theoretically and empirically, that when the dimension of the ambient space is high relative to the sum of the dimensions of the affine subspaces, the affine constraint has a negligible effect on clustering performance. Specifically, our analysis provides conditions that guarantee the correctness of affine subspace clustering methods both with and without the affine constraint, and shows that these conditions are satisfied for high-dimensional data. Underlying our analysis is the notion of affinely independent subspaces, which not only provides geometrically interpretable correctness conditions, but also clarifies the relationships between existing results for affine subspace clustering.

Dual Principal Component Pursuit (DPCP) is a recently proposed non-convex optimization based method for learning subspaces of high relative dimension from noiseless datasets contaminated by as many outliers as the square of the number of inliers. Experimentally, DPCP has proved to be robust to noise and outperform the popular RANSAC on 3D vision tasks such as road plane detection and relative poses estimation from three views. This paper extends the global optimality and convergence theory of DPCP to the case of data corrupted by noise, and further demonstrates its robustness using synthetic and real data.

Minimizing a non-smooth function over the Grassmannian appears in many applications in machine learning. In this paper we show that if the objective satisfies a certain Riemannian regularity condition with respect to some point in the Grassmannian, then a Riemannian subgradient method with appropriate initialization and geometrically diminishing step size converges at a linear rate to that point. We show that for both the robust subspace learning method Dual Principal Component Pursuit (DPCP) and the Orthogonal Dictionary Learning (ODL) problem, the Riemannian regularity condition is satisfied with respect to appropriate points of interest, namely the subspace orthogonal to the sought subspace for DPCP and the orthonormal dictionary atoms for ODL. Consequently, we obtain in a unified framework significant improvements for the convergence theory of both methods.

Recently, there has been an increasing interest in using tools from dynamical systems to analyze the behavior of simple optimization algorithms such as gradient descent and accelerated variants. This paper strengthens such connections by deriving the differential equations that model the continuous limit of the sequence of iterates generated by the alternating direction method of multipliers, as well as an accelerated variant. We employ the direct method of Lyapunov to analyze the stability of critical points of the dynamical systems and to obtain associated convergence rates.

Recent methods for learning a linear subspace from data corrupted by outliers are based on convex L1 and nuclear norm optimization and require the dimension of the subspace and the number of outliers to be sufficiently small [27]. In sharp contrast, the recently proposed Dual Principal Component Pursuit (DPCP) method [22] can provably handle subspaces of high dimension by solving a non-convex L1 optimization problem on the sphere. However, its geometric analysis is based on quantities that are difficult to interpret and are not amenable to statistical analysis. In this paper we provide a refined geometric analysis and a new statistical analysis that show that DPCP can tolerate as many outliers as the square of the number of inliers, thus improving upon other provably correct robust PCA methods. We also propose a scalable Projected Sub-Gradient Descent method (DPCP-PSGD) for solving the DPCP problem and show it admits linear convergence even though the underlying optimization problem is non-convex and non-smooth. Experiments on road plane detection from 3D point cloud data demonstrate that DPCP-PSGD can be more efficient than the traditional RANSAC algorithm, which is one of the most popular methods for such computer vision applications.

Many computer vision tasks involve processing large amounts of data contaminated by outliers, which need to be detected and rejected. While outlier detection methods based on robust statistics have existed for decades, only recently have methods based on sparse and low-rank representation been developed along with guarantees of correct outlier detection when the inliers lie in one or more low-dimensional subspaces. This paper proposes a new outlier detection method that combines tools from sparse representation with random walks on a graph. By exploiting the property that data points can be expressed as sparse linear combinations of each other, we obtain an asymmetric affinity matrix among data points, which we use to construct a weighted directed graph. By defining a suitable Markov Chain from this graph, we establish a connection between inliers/outliers and essential/inessential states of the Markov chain, which allows us to detect outliers by using random walks. We provide a theoretical analysis that justifies the correctness of our method under geometric and connectivity assumptions. Experimental results on image databases demonstrate its superiority with respect to state-of-the-art sparse and low-rank outlier detection methods.

State-of-the-art subspace clustering methods are based on expressing each data point as a linear combination of other data points while regularizing the matrix of coefficients with ℓ1, ℓ2or nuclear norms. ℓ1regularization is guaranteed to give a subspace-preserving affinity (i.e., there are no connections between points from different subspaces) under broad theoretical conditions, but the clusters may not be connected. ℓ2and nuclear norm regularization often improve connectivity, but give a subspace-preserving affinity only for independent subspaces. Mixed ℓ1, ℓ2and nuclear norm regularizations offer a balance between the subspace-preserving and connectedness properties, but this comes at the cost of increased computational complexity. This paper studies the geometry of the elastic net regularizer (a mixture of the ℓ1and ℓ2norms) and uses it to derive a provably correct and scalable active set method for finding the optimal coefficients. Our geometric analysis also provides a theoretical justification and a geometric interpretation for the balance between the connectedness (due to ℓ2regularization) and subspace-preserving (due to ℓ1regularization) properties for elastic net subspace clustering. Our experiments show that the proposed active set method not only achieves state-of-the-art clustering performance, but also efficiently handles large-scale datasets.

Subspace clustering methods based on ℓ1, ℓ2or nuclear norm regularization have become very popular due to their simplicity, theoretical guarantees and empirical success. However, the choice of the regularizer can greatly impact both theory and practice. For instance, ℓ1regularization is guaranteed to give a subspace-preserving affinity (i.e., there are no connections between points from different subspaces) under broad conditions (e.g., arbitrary subspaces and corrupted data). However, it requires solving a large scale convex optimization problem. On the other hand, ℓ2and nuclear norm regularization provide efficient closed form solutions, but require very strong assumptions to guarantee a subspace-preserving affinity, e.g., independent subspaces and uncorrupted data. In this paper we study a subspace clustering method based on orthogonal matching pursuit. We show that the method is both computationally efficient and guaranteed to give a subspace-preserving affinity under broad conditions. Experiments on synthetic data verify our theoretical analysis, and applications in handwritten digit and face clustering show that our approach achieves the best trade off between accuracy and efficiency. Moreover, our approach is the first one to handle 100,000 data points.

We consider the problem of clustering incomplete data drawn from a union of subspaces. Classical subspace clustering methods are not applicable to this problem because the data are incomplete, while classical low-rank matrix completion methods may not be applicable because data in multiple subspaces may not be low rank. This paper proposes and evaluates two new approaches for subspace clustering and completion. The first one generalizes the sparse subspace clustering algorithm so that it can obtain a sparse representation of the data using only the observed entries. The second one estimates a suitable kernel matrix by assuming a random model for the missing entries and obtains the sparse representation from this kernel. Experiments on synthetic and real data show the advantages and disadvantages of the proposed methods, which all outperform the natural approach (low-rank matrix completion followed by sparse subspace clustering) when the data matrix is high-rank or the percentage of missing entries is large.