Zhizhen Zhao

Prof. Zhizhen Zhao


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 November 2017 in IEEE Transactions on Signal Processing
Verified
Journal Article
Open access
TBTamir Bendory
Tamir Bendory
NBNicolas Boumal
Nicolas Boumal
CMChao Ma
Chao Ma
ZZZhizhen Zhao
Zhizhen Zhao
ASAmit Singer
Amit Singer
We consider the problem of estimating a signal from noisy circularly translated versions of itself, called multireference alignment (MRA). One natural approach to MRA could be to estimate the shifts of the observations first, and infer the signal by aligning and averaging the data. In contrast, we consider a method based on estimating the signal directly, using features of the signal that are invariant under translations. Specifically, we estimate the power spectrum and the bispectrum of the signal from the observations. Under mild assumptions, these invariant features contain enough information to infer the signal. In particular, the bispectrum can be used to estimate the Fourier phases. To this end, we propose and analyze a few algorithms. Our main methods consist of nonconvex optimization over the smooth manifold of phases. Empirically, in the absence of noise, these nonconvex algorithms appear to converge to the target signal with random initialization. The algorithms are also robust to noise. We then suggest three additional methods. These methods are based on frequency marching, semidefinite relaxation, and integer programming. The first two methods provably recover the phases exactly in the absence of noise. In the high noise level regime, the invariant features approach for MRA results in stable estimation if the number of measurements scales like the cube of the noise variance, which is the information-theoretic rate. Additionally, it requires only one pass over the data, which is important at low signal-to-noise ratio when the number of observations must be large.

1 April 2014 in Journal of Structural Biology
Verified
Journal Article
Closed access
ZZZhizhen Zhao
Zhizhen Zhao
ASAmit Singer
Amit Singer

12 August 2016 in Nonlinearity
Verified
Journal Article
Open access
PDF file
ZZZhizhen Zhao
Zhizhen Zhao
DGDimitrios Giannakis
Dimitrios Giannakis
Analog forecasting is a nonparametric technique introduced by Lorenz in 1969 which predicts the evolution of states of a dynamical system (or observables defined on the states) by following the evolution of the sample in a historical record of observations which most closely resembles the current initial data. Here, we introduce a suite of forecasting methods which improve traditional analog forecasting by combining ideas from kernel methods developed in harmonic analysis and machine learning and state-space reconstruction for dynamical systems. A key ingredient of our approach is to replace single-analog forecasting with weighted ensembles of analogs constructed using local similarity kernels. The kernels used here employ a number of dynamics-dependent features designed to improve forecast skill, including Takens’ delay-coordinate maps (to recover information in the initial data lost through partial observations) and a directional dependence on the dynamical vector field generating the data. Mathematically, our approach is closely related to kernel methods for out-of-sample extension of functions, and we discuss alternative strategies based on the Nyström method and the multiscale Laplacian pyramids technique. We illustrate these techniques in applications to forecasting in a low-order deterministic model for atmospheric dynamics with chaotic metastability, and interannual-scale forecasting in the North Pacific sector of a comprehensive climate model. We find that forecasts based on kernel-weighted ensembles have significantly higher skill than the conventional approach following a single analog.

18 January 2016 in IEEE Transactions on Computational Imaging
Verified
Journal Article
Open access
ZZZhizhen Zhao
Zhizhen Zhao
YSYoel Shkolnisky
Yoel Shkolnisky
ASAmit Singer
Amit Singer
Cryo-electron microscopy nowadays often requires the analysis of hundreds of thousands of 2-D images as large as a few hundred pixels in each direction. Here, we introduce an algorithm that efficiently and accurately performs principal component analysis (PCA) for a large set of 2-D images, and, for each image, the set of its uniform rotations in the plane and their reflections. For a dataset consisting of n images of size L × L pixels, the computational complexity of our algorithm is O(nL 3 + L 4 ), while existing algorithms take O(nL 4 ). The new algorithm computes the expansion coefficients of the images in a Fourier-Bessel basis efficiently using the nonuniform fast Fourier transform. We compare the accuracy and efficiency of the new algorithm with traditional PCA and existing algorithms for steerable PCA.

30 November 2021 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
HSHongyu Shen
Hongyu Shen
EHEliu A Huerta
Eliu A Huerta
EOEamonn O’sHea
Eamonn O’sHea
PKPrayush Kumar
Prayush Kumar
ZZZhizhen Zhao
Zhizhen Zhao
We introduce deep learning models to estimate the masses of the binary components of black hole mergers, (m1,m2) , and three astrophysical properties of the post-merger compact remnant, namely, the final spin, af , and the frequency and damping time of the ringdown oscillations of the fundamental ℓ=m=2 bar mode, (ωR,ωI) . Our neural networks combine a modifiedWaveNetarchitecture with contrastive learning and normalizing flow. We validate these models against a Gaussian conjugate prior family whose posterior distribution is described by a closed analytical expression. Upon confirming that our models produce statistically consistent results, we used them to estimate the astrophysical parameters (m1,m2,af,ωR,ωI) of five binary black holes:GW150914,GW170104,GW170814,GW190521andGW190630. We usePyCBC Inferenceto directly compare traditional Bayesian methodologies for parameter estimation with our deep learning based posterior distributions. Our results show that our neural network models predict posterior distributions that encode physical correlations, and that our data-driven median results and 90% confidence intervals are similar to those produced with gravitational wave Bayesian analyses. This methodology requires a single V100NVIDIAGPU to produce median values and posterior distributions within two milliseconds for each event. This neural network, and a tutorial for its use, are available at theData and Learning Hub for Science.

2 January 2023 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
ZZZhizhen Zhao
Zhizhen Zhao
JYJong Chul Ye
Jong Chul Ye
YBYoram Bresler
Yoram Bresler
Physics-informed generative modeling for inverse problems in computational imaging is a fast-growing field encompassing a variety of methods and applications. Here, we review a few generative modeling techniques, such as variational autoencoders (VAEs) and generative adversarial networks (GANs), as well as more recent developments in score-based generative models. Through different imaging applications, we review how the generative modeling techniques are effectively combined with the physics of the imaging problem, e.g., the measurement forward model and physical properties of the target objects, to solve the inverse problems.