Search Results for author: Xiaotong Yuan

Found 10 papers, 3 papers with code

Deconvolution in Fluorescence Lifetime imaging microscopy (FLIM)

no code implementations16 Jan 2022 Varun Mannam, Xiaotong Yuan, Scott Howard

Fluorescence lifetime imaging microscopy (FLIM) is an important technique to understand the chemical micro-environment in cells and tissues since it provides additional contrast compared to conventional fluorescence imaging.

Towards Understanding Why Lookahead Generalizes Better Than SGD and Beyond

1 code implementation NeurIPS 2021 Pan Zhou, Hanshu Yan, Xiaotong Yuan, Jiashi Feng, Shuicheng Yan

Specifically, we prove that lookahead using SGD as its inner-loop optimizer can better balance the optimization error and generalization error to achieve smaller excess risk error than vanilla SGD on (strongly) convex problems and nonconvex problems with Polyak-{\L}ojasiewicz condition which has been observed/proved in neural networks.

Boosting the Confidence of Near-Tight Generalization Bounds for Uniformly Stable Randomized Algorithms

no code implementations29 Sep 2021 Xiaotong Yuan, Ping Li

We further substantialize these generic results to SGD to derive improved high probability generalization bounds for convex or non-convex optimization with natural time decaying learning rates, which have not been possible to prove with the existing uniform stability results.

Generalization Bounds Open-Ended Question Answering

Deep learning-based super-resolution fluorescence microscopy on small datasets

1 code implementation7 Mar 2021 Varun Mannam, Yide Zhang, Xiaotong Yuan, Scott Howard

However, using the new approach, a network can be trained to achieve super-resolution images from this small dataset.


Hyperspectral image classification using spectral-spatial LSTMs

no code implementations20 Aug 2018 Feng Zhou, Renlong Hang, Qingshan Liu, Xiaotong Yuan

Specifically, for each pixel, we feed its spectral values in different channels into Spectral LSTM one by one to learn the spectral feature.

Classification General Classification +1

A New Theory for Matrix Completion

no code implementations NeurIPS 2017 Guangcan Liu, Qingshan Liu, Xiaotong Yuan

To break through the limits of random sampling, this paper introduces a new hypothesis called \emph{isomeric condition}, which is provably weaker than the assumption of uniform sampling and arguably holds even when the missing data is placed irregularly.

Matrix Completion

Learning Additive Exponential Family Graphical Models via \ell_{2,1}-norm Regularized M-Estimation

no code implementations NeurIPS 2016 Xiaotong Yuan, Ping Li, Tong Zhang, Qingshan Liu, Guangcan Liu

We investigate a subclass of exponential family graphical models of which the sufficient statistics are defined by arbitrary additive forms.

Exact Recovery of Hard Thresholding Pursuit

no code implementations NeurIPS 2016 Xiaotong Yuan, Ping Li, Tong Zhang

In this paper, we bridge this gap by showing, for the first time, that exact recovery of the global sparse minimizer is possible for HTP-style methods under restricted strong condition number bounding conditions.

Information-Theoretic Measures for Objective Evaluation of Classifications

no code implementations10 Jul 2011 Bao-Gang Hu, Ran He, Xiaotong Yuan

This work presents a systematic study of objective evaluations of abstaining classifications using Information-Theoretic Measures (ITMs).

Cannot find the paper you are looking for? You can Submit a new open access paper.