no code implementations • 28 Nov 2022 • Zai Yang, Yi-Lin Mo, Gongguo Tang, Zongben Xu
Atomic norm methods have recently been proposed for spectral super-resolution with flexibility in dealing with missing data and miscellaneous noises.
no code implementations • 9 Jul 2022 • Zhen Qin, Alexander Lidiak, Zhexuan Gong, Gongguo Tang, Michael B. Wakin, Zhihui Zhu
Tensor train decomposition is widely used in machine learning and quantum physics due to its concise representation of high-dimensional tensors, overcoming the curse of dimensionality.
1 code implementation • NeurIPS 2019 • Zhihui Zhu, Qiuwei Li, Xinshuo Yang, Gongguo Tang, Michael B. Wakin
Low-rank matrix factorization is a problem of broad importance, owing to the ubiquity of low-rank models in machine learning contexts.
no code implementations • NeurIPS 2019 • Shuang Li, Gongguo Tang, Michael B. Wakin
We also apply the theory to matrix sensing and phase retrieval to demonstrate how to infer the landscape of empirical risk from that of the corresponding population risk.
no code implementations • 22 Apr 2019 • Qiuwei Li, Zhihui Zhu, Gongguo Tang, Michael B. Wakin
Therefore, this work not only develops guaranteed optimization methods for non-Lipschitz smooth problems but also solves an open problem of showing the second-order convergence guarantees for these alternating minimization methods.
1 code implementation • 16 Mar 2019 • Kai Liu, Qiuwei Li, Hua Wang, Gongguo Tang
However, most of the studies on PCA aim to minimize the loss after projection, which usually measures the Euclidean distance, though in some fields, angle distance is known to be more important and critical for analysis.
no code implementations • 7 Nov 2018 • Zhihui Zhu, Qiuwei Li, Xinshuo Yang, Gongguo Tang, Michael B. Wakin
We study the convergence of a variant of distributed gradient descent (DGD) on a distributed low-rank matrix approximation problem wherein some optimization variables are used for consensus (as in classical DGD) and some optimization variables appear only locally at a single node in the network.
no code implementations • 5 Apr 2017 • Qiuwei Li, Zhihui Zhu, Gongguo Tang
In spite of the nonconvexity of the factored formulation, we prove that when the convex loss function $f(X)$ is $(2r, 4r)$-restricted well-conditioned, each critical point of the factored problem either corresponds to the optimal solution $X^\star$ of the original convex optimization or is a strict saddle point where the Hessian matrix has a strictly negative eigenvalue.
no code implementations • NeurIPS 2015 • Parikshit Shah, Nikhil Rao, Gongguo Tang
Our method relies on a reduction of the problem to sparse and low-rank matrix decomposition via the notion of tensor contraction.
no code implementations • 10 Nov 2015 • Li-Hao Yeh, Jonathan Dong, Jingshan Zhong, Lei Tian, Michael Chen, Gongguo Tang, Mahdi Soltanolkotabi, Laura Waller
Both noise (e. g. Poisson noise) and model mis-match errors are shown to scale with intensity.
no code implementations • 15 May 2015 • Parikshit Shah, Nikhil Rao, Gongguo Tang
This motivates us to consider the problem of low rank tensor recovery from a class of linear measurements called separable measurements.
no code implementations • IEEE Transactions on Information Theory ( Volume: 59, Issue: 11, November 2013) 2013 • Gongguo Tang
This paper investigates the problem of estimating the frequency components of a mixture of complex sinusoids from a random subset of regularly spaced samples.
no code implementations • 6 Sep 2012 • Matthew L. Malloy, Gongguo Tang, Robert D. Nowak
We consider a large number of populations, each corresponding to either distribution P0 or P1.
1 code implementation • 3 Apr 2012 • Badri Narayan Bhaskar, Gongguo Tang, Benjamin Recht
Motivated by recent work on atomic norms in inverse problems, we propose a new approach to line spectral estimation that provides theoretical guarantees for the mean-squared-error (MSE) performance in the presence of noise and without knowledge of the model order.
Information Theory Information Theory