# Publications by Year: 2017

2017
C. Wang, J. Mattingly, and Y. M. Lu, “Scaling Limit: Exact and Tractable Analysis of Online Learning Algorithms with Applications to Regularized Regression and PCA,” Technical Report, 2017. arXiv:1712.04332 [cs.LG]Abstract
We present a framework for analyzing the exact dynamics of a class of online learning algorithms in the high-dimensional scaling limit. Our results are applied to two concrete examples: online regularized linear regression and principal component analysis. As the ambient dimension tends to infinity, and with proper time scaling, we show that the time-varying joint empirical measures of the target feature vector and its estimates provided by the algorithms will converge weakly to a deterministic measured-valued process that can be characterized as the unique solution of a nonlinear PDE. Numerical solutions of this PDE can be efficiently obtained. These solutions lead to precise predictions of the performance of the algorithms, as many practical performance metrics are linear functionals of the joint empirical measures. In addition to characterizing the dynamic performance of online learning algorithms, our asymptotic analysis also provides useful insights. In particular, in the high-dimensional limit, and due to exchangeability, the original coupled dynamics associated with the algorithms will be asymptotically decoupled'', with each coordinate independently solving a 1-D effective minimization problem via stochastic gradient descent. Exploiting this insight for nonconvex optimization problems may prove an interesting line of future research.
O. Dhifallah, C. Thrampoulidis, and Y. M. Lu, “Phase Retrieval via Linear Programming: Fundamental Limits and Algorithmic Improvements,” in 55th Annual Allerton Conference on Communication, Control, and Computing, 2017. arXiv:1710.05234 [cs.IT]Abstract
A recently proposed convex formulation of the phase retrieval problem estimates the unknown signal by solving a simple linear program. This new scheme, known as PhaseMax, is computationally efficient compared to standard convex relaxation methods based on lifting techniques. In this paper, we present an exact performance analysis of PhaseMax under Gaussian measurements in the large system limit. In contrast to previously known performance bounds in the literature, our results are asymptotically exact and they also reveal a sharp phase transition phenomenon. Furthermore, the geometrical insights gained from our analysis led us to a novel nonconvex formulation of the phase retrieval problem and an accompanying iterative algorithm based on successive linearization and maximization over a polytope. This new algorithm, which we call PhaseLamp, has provably superior recovery performance over the original PhaseMax method.
C. Wang and Y. M. Lu, “The Scaling Limit of High-Dimensional Online Independent Component Analysis,” in Conference on Neural Information Processing Systems (NIPS), 2017.Abstract

We analyze the dynamics of an online algorithm for independent component analysis in the high-dimensional scaling limit. As the ambient dimension tends to infinity, and with proper time scaling, we show that the time-varying joint empirical measure of the target feature vector and the estimates provided by the algorithm will converge weakly to a deterministic measured-valued process that can be characterized as the unique solution of a nonlinear PDE. Numerical solutions of this PDE, which involves two spatial variables and one time variable, can be efficiently obtained. These solutions provide detailed information about the performance of the ICA algorithm, as many practical performance metrics are functionals of the joint empirical measures. Numerical simulations show that our asymptotic analysis is accurate even for moderate dimensions. In addition to providing a tool for understanding the performance of the algorithm, our PDE analysis also provides useful insight. In particular, in the high-dimensional limit, the original coupled dynamics associated with the algorithm will be asymptotically “decoupled”, with each coordinate independently solving a 1-D effective minimization problem via stochastic gradient descent. Exploiting this insight to design new algorithms for achieving optimal trade-offs between computational and statistical efficiency may prove an interesting line of future research.

Spotlight paper (acceptance rate: 112/3240 = 3.5%)
O. Dhifallah and Y. M. Lu, “Fundamental Limits of PhaseMax for Phase Retrieval: A Replica Analysis,” in the 7th IEEE Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2017. arXiv:1708.03355Abstract

We consider a recently proposed convex formulation, known as the PhaseMax method, for solving the phase retrieval problem. Using the replica method from statistical mechanics, we analyze the performance of PhaseMax in the high-dimensional limit. Our analysis predicts the exact asymptotic performance of PhaseMax. In particular, we show that a sharp phase transi- tion phenomenon takes place, with a simple analytical formula characterizing the phase transition boundary. This result shows that the oversampling ratio required by existing performance bounds in the literature can be significantly reduced. Numerical results confirm the validity of our replica analysis, showing that the theoretical predictions are in excellent agreement with the actual performance of the algorithm, even for moderate signal dimensions.

This paper won the Best Student Paper Award (First Prize) at the 2017 IEEE CAMSAP Workshop.

The predictions made in this paper via the non-rigorous replica method has since been rigorously established in our latest work.

Y. M. Lu and G. Li, “Spectral Initialization for Nonconvex Estimation: High-Dimensional Limit and Phase Transitions,” in IEEE International Symposium on Information Theory (ISIT), 2017.Abstract

We study a simple spectral method that serves as a key ingredient in a growing line of work using efficient iterative algorithms for estimating signals in nonconvex settings. Unlike previous work, which focuses on the phase retrieval setting and provides only bounds on the performance, we consider arbitrary generalized linear sensing models and provide an exact characterization of the performance of the spectral method in the high-dimensional regime. Our analysis reveals a phase transition phenomenon that depends on the sampling ratio. When the ratio is below a critical threshold, the estimates given by the spectral method are no better than random guesses drawn uniformly from the hypersphere; above the threshold, however, the estimates become increasingly aligned with the underlying signal. Worked examples and numerical simulations are provided to illustrate and verify the analytical predictions.

C. Wang, Y. Eldar, and Y. M. Lu, “Subspace Estimation from Incomplete Observations: A Precise High-Dimensional Analysis,” in Signal Processing with Adaptive Structured Representatives (SPARS) Workshop, 2017.Abstract

The problem of estimating and tracking low-rank subspaces from incomplete observations has received a lot of attention recently in the signal processing and learning communities. Popular algorithms, such as GROUSE and PETRELS, are often very effective in practice, but their performance depends on the careful choice of algorithmic parameters. Important questions, such as the global convergence of these algorithms and how the noise level, subsampling ratio, and various other parameters affect the performance, are not fully understood. In this paper, we present a precise analysis of the performance of these algorithms in the asymptotic regime where the ambient dimension tends to infinity. Specifically, we show that the time-varying trajectories of estimation errors converge weakly to a deterministic function of time, which is characterized as the unique solution of a system of ordinary differential equations (ODEs.) Analyzing the limiting ODEs also reveals and characterizes sharp phase transition phenomena associated with these algorithms. Numerical simulations verify the accuracy of our asymptotic predictions, even for moderate signal dimensions.

R. Yin, T. Gao, Y. M. Lu, and I. Daubechies, “A Tale of Two Bases: Local-Nonlocal Regularization on Image Patches with Convolution Framelets,” SIAM Journal on Imaging Sciences, vol. 10, no. 2, pp. 711-750, 2017.Abstract

We propose an image representation scheme combining the local and nonlocal characterization of patches in an image. Our representation scheme can be shown to be equivalent to a tight frame constructed from convolving local bases (e.g., wavelet frames, discrete cosine transforms, etc.) with nonlocal bases (e.g., spectral basis induced by nonlinear dimension reduction on patches), and we call the resulting frame elements convolution framelets. Insight gained from analyzing the proposed representation leads to a novel interpretation of a recent high-performance patch-based image pro- cessing algorithm using the point integral method (PIM) and the low dimensional manifold model (LDMM) [S. Osher, Z. Shi, and W. Zhu, Low Dimensional Manifold Model for Image Processing, Tech. Rep., CAM report 16-04, UCLA, Los Angeles, CA, 2016]. In particular, we show that LDMM is a weighted l2-regularization on the coefficients obtained by decomposing images into linear combinations of convolution framelets; based on this understanding, we extend the original LDMM to a reweighted version that yields further improved results. In addition, we establish the energy concentration property of convolution framelet coefficients for the setting where the local basis is constructed from a given nonlocal basis via a linear reconstruction framework; a generalization of this framework to unions of local embeddings can provide a natural setting for interpreting BM3D, one of the state-of-the-art image denoising algorithms.

S. H. Chan, T. Zickler, and Y. M. Lu, “Understanding Symmetric Smoothing Filters: A Gaussian Mixture Model Perspective,” IEEE Transactions on Image Processing, vol. 26, no. 11, pp. 5107-5121, 2017. arXiv:1601.00088Abstract

Many patch-based image denoising algorithms can be formulated as applying a smoothing filter to the noisy image. Expressed as matrices, the smoothing filters must be row normalized so that each row sums to unity. Surprisingly, if we apply a column normalization before the row normalization, the performance of the smoothing filter can often be significantly improved. Prior works showed that such performance gain is related to the Sinkhorn-Knopp balancing algorithm, an iterative procedure that symmetrizes a row-stochastic matrix to a doubly-stochastic matrix. However, a complete understanding of the performance gain phenomenon is still lacking.

In this paper, we study the performance gain phenomenon from a statistical learning perspective. We show that Sinkhorn-Knopp is equivalent to an Expectation-Maximization (EM) algorithm of learning a Product of Gaussians (PoG) prior of the image patches. By establishing the correspondence between the steps of Sinkhorn-Knopp and the EM algorithm, we provide a geometrical interpretation of the symmetrization process. The new PoG model also allows us to develop a new denoising algorithm called Product of Gaussian Non-Local-Means (PoG-NLM). PoG-NLM is an extension of the Sinkhorn-Knopp and is a generalization of the classical non-local means. Despite its simple formulation, PoG-NLM outperforms many existing smoothing filters and has a similar performance compared to BM3D.