Alert button
Picture for Christopher Musco

Christopher Musco

Alert button

The Statistical Cost of Robust Kernel Hyperparameter Tuning

Jun 14, 2020
Raphael A. Meyer, Christopher Musco

This paper studies the statistical complexity of kernel hyperparameter tuning in the setting of active regression under adversarial noise. We consider the problem of finding the best interpolant from a class of kernels with unknown hyperparameters, assuming only that the noise is square-integrable. We provide finite-sample guarantees for the problem, characterizing how increasing the complexity of the kernel class increases the complexity of learning kernel hyperparameters. For common kernel classes (e.g. squared-exponential kernels with unknown lengthscale), our results show that hyperparameter optimization increases sample complexity by just a logarithmic factor, in comparison to the setting where optimal parameters are known in advance. Our result is based on a subsampling guarantee for linear regression under multiple design matrices, combined with an {\epsilon}-net argument for discretizing kernel parameterizations.

Viaarxiv icon

Fourier Sparse Leverage Scores and Approximate Kernel Learning

Jun 12, 2020
Tamás Erdélyi, Cameron Musco, Christopher Musco

Figure 1 for Fourier Sparse Leverage Scores and Approximate Kernel Learning
Figure 2 for Fourier Sparse Leverage Scores and Approximate Kernel Learning
Figure 3 for Fourier Sparse Leverage Scores and Approximate Kernel Learning
Figure 4 for Fourier Sparse Leverage Scores and Approximate Kernel Learning

We prove new explicit upper bounds on the leverage scores of Fourier sparse functions under both the Gaussian and Laplace measures. In particular, we study $s$-sparse functions of the form $f(x) = \sum_{j=1}^s a_j e^{i \lambda_j x}$ for coefficients $a_j \in \mathbb{C}$ and frequencies $\lambda_j \in \mathbb{R}$. Bounding Fourier sparse leverage scores under various measures is of pure mathematical interest in approximation theory, and our work extends existing results for the uniform measure [Erd17,CP19a]. Practically, our bounds are motivated by two important applications in machine learning: 1. Kernel Approximation. They yield a new random Fourier features algorithm for approximating Gaussian and Cauchy (rational quadratic) kernel matrices. For low-dimensional data, our method uses a near optimal number of features, and its runtime is polynomial in the $statistical\ dimension$ of the approximated kernel matrix. It is the first "oblivious sketching method" with this property for any kernel besides the polynomial kernel, resolving an open question of [AKM+17,AKK+20b]. 2. Active Learning. They can be used as non-uniform sampling distributions for robust active learning when data follows a Gaussian or Laplace distribution. Using the framework of [AKM+19], we provide essentially optimal results for bandlimited and multiband interpolation, and Gaussian process regression. These results generalize existing work that only applies to uniformly distributed data.

Viaarxiv icon

Projection-Cost-Preserving Sketches: Proof Strategies and Constructions

Apr 17, 2020
Cameron Musco, Christopher Musco

Figure 1 for Projection-Cost-Preserving Sketches: Proof Strategies and Constructions

In this note we illustrate how common matrix approximation methods, such as random projection and random sampling, yield projection-cost-preserving sketches, as introduced in [FSS13, CEM+15]. A projection-cost-preserving sketch is a matrix approximation which, for a given parameter $k$, approximately preserves the distance of the target matrix to all $k$-dimensional subspaces. Such sketches have applications to scalable algorithms for linear algebra, data science, and machine learning. Our goal is to simplify the presentation of proof techniques introduced in [CEM+15] and [CMM17] so that they can serve as a guide for future work. We also refer the reader to [CYD19], which gives a similar simplified exposition of the proof covered in Section 2.

Viaarxiv icon

Sample Efficient Toeplitz Covariance Estimation

Jun 06, 2019
Yonina C. Eldar, Jerry Li, Cameron Musco, Christopher Musco

Figure 1 for Sample Efficient Toeplitz Covariance Estimation
Figure 2 for Sample Efficient Toeplitz Covariance Estimation
Figure 3 for Sample Efficient Toeplitz Covariance Estimation
Figure 4 for Sample Efficient Toeplitz Covariance Estimation

We study the sample complexity of estimating the covariance matrix $T$ of a distribution $\mathcal{D}$ over $d$-dimensional vectors, under the assumption that $T$ is Toeplitz. This assumption arises in many signal processing problems, where the covariance between any two measurements only depends on the time or distance between those measurements. We are interested in estimation strategies that may choose to view only a subset of entries in each vector sample $x \sim \mathcal{D}$, which often equates to reducing hardware and communication requirements in applications ranging from wireless signal processing to advanced imaging. Our goal is to minimize both 1) the number of vector samples drawn from $\mathcal{D}$ and 2) the number of entries accessed in each sample. We provide some of the first non-asymptotic bounds on these sample complexity measures that exploit $T$'s Toeplitz structure, and by doing so, significantly improve on results for generic covariance matrices. Our bounds follow from a novel analysis of classical and widely used estimation algorithms (along with some new variants), including methods based on selecting entries from each vector sample according to a so-called sparse ruler. In many cases, we pair our upper bounds with matching or nearly matching lower bounds. In addition to results that hold for any Toeplitz $T$, we further study the important setting when $T$ is close to low-rank, which is often the case in practice. We show that methods based on sparse rulers perform even better in this setting, with sample complexity scaling sublinearly in $d$. Motivated by this finding, we develop a new covariance estimation strategy that further improves on all existing methods in the low-rank case: when $T$ is rank-$k$ or nearly rank-$k$, it achieves sample complexity depending polynomially on $k$ and only logarithmically on $d$.

Viaarxiv icon

Low-Rank Approximation from Communication Complexity

Apr 22, 2019
Cameron Musco, Christopher Musco, David P. Woodruff

Figure 1 for Low-Rank Approximation from Communication Complexity

In low-rank approximation with missing entries, given $A\in \mathbb{R}^{n\times n}$ and binary $W \in \{0,1\}^{n\times n}$, the goal is to find a rank-$k$ matrix $L$ for which: $$cost(L)=\sum_{i=1}^{n} \sum_{j=1}^{n}W_{i,j}\cdot (A_{i,j} - L_{i,j})^2\le OPT+\epsilon \|A\|_F^2,$$ where $OPT=\min_{rank-k\ \hat{L}}cost(\hat L)$. This problem is also known as matrix completion and, depending on the choice of $W$, captures low-rank plus diagonal decomposition, robust PCA, low-rank recovery from monotone missing data, and a number of other important problems. Many of these problems are NP-hard, and while algorithms with provable guarantees are known in some cases, they either 1) run in time $n^{\Omega(k^2/\epsilon)}$, or 2) make strong assumptions, e.g., that $A$ is incoherent or that $W$ is random. In this work, we consider $bicriteria\ algorithms$, which output $L$ with rank $k' > k$. We prove that a common heuristic, which simply sets $A$ to $0$ where $W$ is $0$, and then computes a standard low-rank approximation, achieves the above approximation bound with rank $k'$ depending on the $communication\ complexity$ of $W$. Namely, interpreting $W$ as the communication matrix of a Boolean function $f(x,y)$ with $x,y\in \{0,1\}^{\log n}$, it suffices to set $k'=O(k\cdot 2^{R^{1-sided}_{\epsilon}(f)})$, where $R^{1-sided}_{\epsilon}(f)$ is the randomized communication complexity of $f$ with $1$-sided error probability $\epsilon$. For many problems, this yields bicriteria algorithms with $k'=k\cdot poly((\log n)/\epsilon)$. We prove a similar bound using the randomized communication complexity with $2$-sided error. Further, we show that different models of communication yield algorithms for natural variants of the problem. E.g., multi-player communication complexity connects to tensor decomposition and non-deterministic communication complexity to Boolean low-rank factorization.

Viaarxiv icon

A Universal Sampling Method for Reconstructing Signals with Simple Fourier Transforms

Dec 20, 2018
Haim Avron, Michael Kapralov, Cameron Musco, Christopher Musco, Ameya Velingker, Amir Zandieh

Figure 1 for A Universal Sampling Method for Reconstructing Signals with Simple Fourier Transforms
Figure 2 for A Universal Sampling Method for Reconstructing Signals with Simple Fourier Transforms
Figure 3 for A Universal Sampling Method for Reconstructing Signals with Simple Fourier Transforms
Figure 4 for A Universal Sampling Method for Reconstructing Signals with Simple Fourier Transforms

Reconstructing continuous signals from a small number of discrete samples is a fundamental problem across science and engineering. In practice, we are often interested in signals with 'simple' Fourier structure, such as bandlimited, multiband, and Fourier sparse signals. More broadly, any prior knowledge about a signal's Fourier power spectrum can constrain its complexity. Intuitively, signals with more highly constrained Fourier structure require fewer samples to reconstruct. We formalize this intuition by showing that, roughly, a continuous signal from a given class can be approximately reconstructed using a number of samples proportional to the *statistical dimension* of the allowed power spectrum of that class. Further, in nearly all settings, this natural measure tightly characterizes the sample complexity of signal reconstruction. Surprisingly, we also show that, up to logarithmic factors, a universal non-uniform sampling strategy can achieve this optimal complexity for *any class of signals*. We present a simple and efficient algorithm for recovering a signal from the samples taken. For bandlimited and sparse signals, our method matches the state-of-the-art. At the same time, it gives the first computationally and sample efficient solution to a broad range of problems, including multiband signal reconstruction and kriging and Gaussian process regression tasks in one dimension. Our work is based on a novel connection between randomized linear algebra and signal reconstruction with constrained Fourier structure. We extend tools based on statistical leverage score sampling and column-based matrix reconstruction to the approximation of continuous linear operators that arise in signal reconstruction. We believe that these extensions are of independent interest and serve as a foundation for tackling a broad range of continuous time problems using randomized methods.

Viaarxiv icon

Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees

May 21, 2018
Haim Avron, Michael Kapralov, Cameron Musco, Christopher Musco, Ameya Velingker, Amir Zandieh

Figure 1 for Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees

Random Fourier features is one of the most popular techniques for scaling up kernel methods, such as kernel ridge regression. However, despite impressive empirical results, the statistical properties of random Fourier features are still not well understood. In this paper we take steps toward filling this gap. Specifically, we approach random Fourier features from a spectral matrix approximation point of view, give tight bounds on the number of Fourier features required to achieve a spectral approximation, and show how spectral matrix approximation bounds imply statistical guarantees for kernel ridge regression. Qualitatively, our results are twofold: on the one hand, we show that random Fourier feature approximation can provably speed up kernel ridge regression under reasonable assumptions. At the same time, we show that the method is suboptimal, and sampling from a modified distribution in Fourier space, given by the leverage function of the kernel, yields provably better performance. We study this optimal sampling distribution for the Gaussian kernel, achieving a nearly complete characterization for the case of low-dimensional bounded datasets. Based on this characterization, we propose an efficient sampling scheme with guarantees superior to random Fourier features in this regime.

* An extended abstract of this work appears in the Proceedings of the 34th International Conference on Machine Learning (ICML 2017) 
Viaarxiv icon

Learning Networks from Random Walk-Based Node Similarities

Jan 23, 2018
Jeremy G. Hoskins, Cameron Musco, Christopher Musco, Charalampos E. Tsourakakis

Figure 1 for Learning Networks from Random Walk-Based Node Similarities
Figure 2 for Learning Networks from Random Walk-Based Node Similarities
Figure 3 for Learning Networks from Random Walk-Based Node Similarities
Figure 4 for Learning Networks from Random Walk-Based Node Similarities

Digital presence in the world of online social media entails significant privacy risks. In this work we consider a privacy threat to a social network in which an attacker has access to a subset of random walk-based node similarities, such as effective resistances (i.e., commute times) or personalized PageRank scores. Using these similarities, the attacker's goal is to infer as much information as possible about the underlying network, including any remaining unknown pairwise node similarities and edges. For the effective resistance metric, we show that with just a small subset of measurements, the attacker can learn a large fraction of edges in a social network, even when the measurements are noisy. We also show that it is possible to learn a graph which accurately matches the underlying network on all other effective resistances. This second observation is interesting from a data mining perspective, since it can be expensive to accurately compute all effective resistances. As an alternative, our graphs learned from just a subset of approximate effective resistances can be used as surrogates in a wide range of applications that use effective resistances to probe graph structure, including for graph clustering, node centrality evaluation, and anomaly detection. We obtain our results by formalizing the graph learning objective mathematically, using two optimization problems. One formulation is convex and can be solved provably in polynomial time. The other is not, but we solve it efficiently with projected gradient and coordinate descent. We demonstrate the effectiveness of these methods on a number of social networks obtained from Facebook. We also discuss how our methods can be generalized to other random walk-based similarities, such as personalized PageRank. Our code is available at https://github.com/cnmusco/graph-similarity-learning.

Viaarxiv icon