371 citations · 896 across the 18 of their papers we have counts for
19 papers
Neural Architecture Search generated Phase Retrieval Net for Real-time Off-axis Quantitative Phase Imaging
Xin Shu, Mengxuan Niu, Yi Zhang +2
In off-axis Quantitative Phase Imaging (QPI), artificial neural networks have been recently applied for phase retrieval with aberration compensation and phase unwrapping. However,…
On Predicting Generalization using GANs
Yi Zhang, Arushi Gupta, Nikunj Saunshi +1
Research on generalization bounds for deep networks seeks to give ways to predict test error using just the training dataset and the network parameters. While generalization bounds…
An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
Yi Zhang
As a promising tool to navigate in the vast chemical space, artificial intelligence (AI) is leveraged for drug design. From the year 2017 to 2021, the number of applications of sev…
DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
Zhizhong Huang, Junping Zhang, Yi Zhang +1
LDCT has drawn major attention in the medical imaging field due to the potential health risks of CT-associated X-ray radiation to patients. Reducing the radiation dose, however, de…
Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction
Qingchao Zhang, Mehrdad Alvandipour, Wenjun Xia +3
We propose a provably convergent method, called Efficient Learned Descent Algorithm (ELDA), for low-dose CT (LDCT) reconstruction. ELDA is a highly interpretable neural network arc…
Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data
Sanjeev Arora, Yi Zhang
Traditional statistics forbids use of test data (a.k.a. holdout data) during training. Dwork et al. 2015 pointed out that current practices in machine learning, whereby researchers…
Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?
Zhiyuan Li, Yi Zhang, Sanjeev Arora
Convolutional neural networks often dominate fully-connected counterparts in generalization performance, especially on image classification tasks. This is often explained in terms…
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning
Nikunj Saunshi, Yi Zhang, Mikhail Khodak +1
One popular trend in meta-learning is to learn from many training tasks a common initialization for a gradient-based method that can be used to solve a new task with few samples. T…
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality
Yi Zhang, Orestis Plevrakis, Simon S. Du +3
Adversarial training is a popular method to give neural nets robustness against adversarial perturbations. In practice adversarial training leads to low robust training loss. Howev…
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
Rohith Kuditipudi, Xiang Wang, Holden Lee +5
Mode connectivity is a surprising phenomenon in the loss landscape of deep nets. Optima -- at least those discovered by gradient-based optimization -- turn out to be connected by s…
STS Classification with Dual-stream CNN
Shuchen Weng, Wenbo Li, Yi Zhang +1
The structured time series (STS) classification problem requires the modeling of interweaved spatiotemporal dependency. most previous STS classification methods model the spatial a…
N2RPP: An Adversarial Network to Rebuild Plantar Pressure for ACLD Patients
Yi Zhang, Zhengfei Wang, Guoxiong Xu +2
Foot is a vital part of human, and lots of valuable information is embedded. Plantar pressure is one of which contains this information and it describes human walking features. It…
Stronger generalization bounds for deep nets via a compression approach
Sanjeev Arora, Rong Ge, Behnam Neyshabur +1
Deep nets generalize well despite having more parameters than the number of training samples. Recent works try to give an explanation using PAC-Bayes and Margin-based analyses, but…
Theoretical limitations of Encoder-Decoder GAN architectures
Sanjeev Arora, Andrej Risteski, Yi Zhang
Encoder-decoder GANs architectures (e.g., BiGAN and ALI) seek to add an inference mechanism to the GANs setup, consisting of a small encoder deep net that maps data-points to their…
Do GANs actually learn the distribution? An empirical study
Sanjeev Arora, Yi Zhang
Do GANS (Generative Adversarial Nets) actually learn the target distribution? The foundational paper of (Goodfellow et al 2014) suggested they do, if they were given sufficiently l…
Towards Understanding the Invertibility of Convolutional Neural Networks
Anna C. Gilbert, Yi Zhang, Kibok Lee +2
Several recent works have empirically observed that Convolutional Neural Nets (CNNs) are (approximately) invertible. To understand this approximate invertibility phenomenon and how…
Generalization and Equilibrium in Generative Adversarial Nets (GANs)
Sanjeev Arora, Rong Ge, Yingyu Liang +2
We show that training of generative adversarial network (GAN) may not have good generalization properties; e.g., training may appear successful but the trained distribution may be…
Convolutional neural networks with low-rank regularization
Cheng Tai, Tong Xiao, Yi Zhang +2
Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these model…
Group Testing with Pools of Fixed Size
David Cariolaro, Zhaiming Shen, Yi Zhang
In the classical combinatorial (adaptive) group testing problem, one is given two integers \(d\) and \(n\), where \(0\le d\le n\), and a population of \(n\) items, exactly \(d\) of…