16 citations · 87 across the 30 of their papers we have counts for
30 papers
Semi-Supervised Conditional Diffusion via Label Augmentation
Jin Su, Yuan Gao, Yong Zhou +1
Conditional diffusion models have become a powerful and flexible framework for learning complex conditional distributions from labeled data. In practice, however, acquiring high-qu…
Lipschitz Transport Maps via the Follmer Flow
Yin Dai, Yuan Gao, Jian Huang +3
Inspired by the construction of the F{ö}llmer process, we construct a unit-time flow on the Euclidean space, termed the F{ö}llmer flow, whose flow map at time 1 pushes forward a st…
Non-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Models
Changyu Liu, Yuling Jiao, Junhui Wang +1
We propose a general approach to evaluating the performance of robust estimators based on adversarial losses under misspecified models. We first show that adversarial risk is equiv…
Differentiable Neural Networks with RePU Activation: with Applications to Score Estimation and Isotonic Regression
Guohao Shen, Yuling Jiao, Yuanyuan Lin +1
We study the properties of differentiable neural networks activated by rectified power unit (RePU) functions. We show that the partial derivatives of RePU neural networks can be re…
Nonparametric Quantile Regression: Non-Crossing Constraints and Conformal Prediction
Wenlu Tang, Guohao Shen, Yuanyuan Lin +1
We propose a nonparametric quantile regression method using deep neural networks with a rectified linear unit penalty function to avoid quantile crossing. This penalty function is…
Deep Sufficient Representation Learning via Mutual Information
Siming Zheng, Yuanyuan Lin, Jian Huang
We propose a mutual information-based sufficient representation learning (MSRL) approach, which uses the variational formulation of the mutual information and leverages the approxi…
Estimation of Non-Crossing Quantile Regression Process with Deep ReQU Neural Networks
Guohao Shen, Yuling Jiao, Yuanyuan Lin +2
We propose a penalized nonparametric approach to estimating the quantile regression process (QRP) in a nonseparable model using rectifier quadratic unit (ReQU) activated deep neura…
Deep Generative Survival Analysis: Nonparametric Estimation of Conditional Survival Function
Xingyu Zhou, Wen Su, Changyu Liu +3
We propose a deep generative approach to nonparametric estimation of conditional survival and hazard functions with right-censored data. The key idea of the proposed method is to f…
Wasserstein Generative Learning of Conditional Distribution
Shiao Liu, Xingyu Zhou, Yuling Jiao +1
Conditional distribution is a fundamental quantity for describing the relationship between a response and a predictor. We propose a Wasserstein generative approach to learning a co…
Non-Asymptotic Error Bounds for Bidirectional GANs
Shiao Liu, Yunfei Yang, Jian Huang +2
We derive nearly sharp bounds for the bidirectional GAN (BiGAN) estimation error under the Dudley distance between the latent joint distribution and the data joint distribution wit…
A Deep Generative Approach to Conditional Sampling
Xingyu Zhou, Yuling Jiao, Jin Liu +1
We propose a deep generative approach to sampling from a conditional distribution based on a unified formulation of conditional distribution and generalized nonparametric regressio…
Relative Entropy Gradient Sampler for Unnormalized Distributions
Xingdong Feng, Yuan Gao, Jian Huang +2
We propose a relative entropy gradient sampler (REGS) for sampling from unnormalized distributions. REGS is a particle method that seeks a sequence of simple nonlinear transforms i…
Deep Quantile Regression: Mitigating the Curse of Dimensionality Through Composition
Guohao Shen, Yuling Jiao, Yuanyuan Lin +2
This paper considers the problem of nonparametric quantile regression under the assumption that the target conditional quantile function is a composition of a sequence of low-dimen…
Robust Nonparametric Regression with Deep Neural Networks
Guohao Shen, Yuling Jiao, Yuanyuan Lin +1
In this paper, we study the properties of robust nonparametric estimation using deep neural networks for regression models with heavy tailed error distributions. We establish the n…
Schr{ö}dinger-F{ö}llmer Sampler: Sampling without Ergodicity
Jian Huang, Yuling Jiao, Lican Kang +3
Sampling from probability distributions is an important problem in statistics and machine learning, specially in Bayesian inference when integration with respect to posterior distr…
An error analysis of generative adversarial networks for learning distributions
Jian Huang, Yuling Jiao, Zhen Li +3
This paper studies how well generative adversarial networks (GANs) learn probability distributions from finite samples. Our main results establish the convergence rates of GANs und…
Non-asymptotic Excess Risk Bounds for Classification with Deep Convolutional Neural Networks
Guohao Shen, Yuling Jiao, Yuanyuan Lin +1
In this paper, we consider the problem of binary classification with a class of general deep convolutional neural networks, which includes fully-connected neural networks and fully…
Deep Nonparametric Regression on Approximate Manifolds: Non-Asymptotic Error Bounds with Polynomial Prefactors
Yuling Jiao, Guohao Shen, Yuanyuan Lin +1
We study the properties of nonparametric least squares regression using deep neural networks. We derive non-asymptotic upper bounds for the prediction error of the empirical risk m…
Generative Learning With Euler Particle Transport
Yuan Gao, Jian Huang, Yuling Jiao +3
We propose an Euler particle transport (EPT) approach for generative learning. The proposed approach is motivated by the problem of finding an optimal transport map from a referenc…
Deep Dimension Reduction for Supervised Representation Learning
Jian Huang, Yuling Jiao, Xu Liao +2
The goal of supervised representation learning is to construct effective data representations for prediction. Among all the characteristics of an ideal nonparametric representation…
Learning Implicit Generative Models with Theoretical Guarantees
Yuan Gao, Jian Huang, Yuling Jiao +1
We propose a \textbf{uni}fied \textbf{f}ramework for \textbf{i}mplicit \textbf{ge}nerative \textbf{m}odeling (UnifiGem) with theoretical guarantees by integrating approaches from o…
-Regularized High-dimensional Accelerated Failure Time Model
Xingdong Feng, Jian Huang, Yuling Jiao +1
We develop a constructive approach for -penalized estimation in the sparse accelerated failure time (AFT) model with high-dimensional covariates. Our proposed method is bas…
A Support Detection and Root Finding Approach for Learning High-dimensional Generalized Linear Models
Jian Huang, Yuling Jiao, Lican Kang +3
Feature selection is important for modeling high-dimensional data, where the number of variables can be much larger than the sample size. In this paper, we develop a support detect…
On Newton Screening
Jian Huang, Yuling Jiao, Lican Kang +4
Screening and working set techniques are important approaches to reducing the size of an optimization problem. They have been widely used in accelerating first-order methods for so…