Neural network training relies on our ability to find" good" minimizers of highly non-convex loss functions. It is well known that certain network architecture designs (eg, skip …
Y Chen, Y Chi, J Fan, C Ma - Foundations and Trends® in …, 2021 - nowpublishers.com
Spectral methods have emerged as a simple yet surprisingly effective approach for extracting information from massive, noisy and incomplete data. In a nutshell, spectral …
Can we recover a complex signal from its Fourier magnitudes? More generally, given a set of m measurements, y_k=\left| a _k^* x\right| yk= ak∗ x for k= 1, ..., mk= 1,…, m, is it possible …
L Zhu, H Yao, H Chang, Q Tian… - IEEE Internet of …, 2022 - ieeexplore.ieee.org
Orbital angular momentum (OAM) has the potential to dramatically enhance the amount of information in the Internet of Underwater Things (IoUT) system. Nevertheless, underwater …
C Ma, K Wang, Y Chi, Y Chen - International Conference on …, 2018 - proceedings.mlr.press
Recent years have seen a flurry of activities in designing provably efficient nonconvex optimization procedures for solving statistical estimation problems. For various problems like …
Generalized linear models (GLMs) are used in high-dimensional machine learning, statistics, communications, and signal processing. In this paper we analyze GLMs when the …
Near-eye displays using holographic projection are emerging as an exciting display approach for virtual and augmented reality at high-resolution without complex optical setups …
We introduce a novel deep-learning inspired formulation of the\textit {phase retrieval problem}, which asks to recover a signal $ y_0\in\R^ n $ from $ m $ quadratic observations …
Holography is arguably the most promising technology to provide wide field-of-view compact eyeglasses-style near-eye displays for augmented and virtual reality. However, the image …