papers

Publications (175)

math.ST2019

How Many Machines Can We Use in Parallel Computing for Kernel Ridge Regression?

Meimei Liu, Zuofeng Shang, Guang Cheng

This paper aims to solve a basic problem in distributed statistical inference: how many machines can we use in parallel computing? In kernel ridge regression, we address this quest…

cs.CR2026

Rate-Distortion Function for Encrypted Traffic Side-Channel Defense

Guangjie Liu, Guang Cheng, Weiwei Liu +1

Parameter selection for encrypted traffic defense has long relied on empirical tuning, yet the fundamental question -- \emph{given a QoS cost budget , how low can the leakage ra…

stat.ML2022

Residual Bootstrap Exploration for Stochastic Linear Bandit

Shuang Wu, Chi-Hua Wang, Yuantong Li +1

We propose a new bootstrap-based online algorithm for stochastic linear bandit problems. The key idea is to adopt residual bootstrap exploration, in which the agent estimates the n…

cs.CR2025

Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis

Joshua Ward, Xiaofeng Lin, Chi-Hua Wang +1

Tabular Generative Models are often argued to preserve privacy by creating synthetic datasets that resemble training data. However, auditing their empirical privacy remains challen…

stat.ML2020

Simultaneous Inference for Massive Data: Distributed Bootstrap

Yang Yu, Shih-Kang Chao, Guang Cheng

In this paper, we propose a bootstrap method applied to massive data processed distributedly in a large number of machines. This new method is computationally efficient in that we…

stat.ME2013

Sparse and Efficient Estimation for Partial Spline Models with Increasing Dimension

Guang Cheng, Hao Helen Zhang, Zuofeng Shang

We consider model selection and estimation for partial spline models and propose a new regularization method in the context of smoothing splines. The regularization method has a si…

cs.CR2025

Unleashing the Power of LLM to Infer State Machine from the Protocol Implementation

Haiyang Wei, Ligeng Chen, Zhengjie Du +7

State machines are essential for enhancing protocol analysis to identify vulnerabilities. However, inferring state machines from network protocol implementations is challenging due…

math.ST2017

Quantile Processes for Semi and Nonparametric Regression

Shih-Kang Chao, Stanislav Volgushev, Guang Cheng

A collection of quantile curves provides a complete picture of conditional distributions. Properly centered and scaled versions of estimated curves at various quantile levels give…

cs.CR2026

A Queueing-Stability Criterion for Causal IPD-QIM Network Flow Watermarking

Jiuxiang Cai, Jiuxiang Cao, Guang Cheng +1

The paper derives a queueing‑theoretic stability condition for embedding causal QIM watermarks in inter‑packet delays of encrypted multi‑hop traffic, showing when the induced delay…

#network flow watermarking#queueing theory#inter-packet delay#causal quantization-index-modulation
stat.ML2024

Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints

Yuantong Li, Guang Cheng, Xiaowu Dai

In this paper, we propose a new recommendation algorithm for addressing the problem of two-sided online matching markets with complementary preferences and quota constraints, where…

cs.CR2019

A Cost-effective Shuffling Method against DDoS Attacks using Moving Target Defense

Yuyang Zhou, Guang Cheng, Shanqing Jiang +3

Moving Target Defense (MTD) has emerged as a newcomer into the asymmetric field of attack and defense, and shuffling-based MTD has been regarded as one of the most effective ways t…

cs.LG2024

Tree-based Ensemble Learning for Out-of-distribution Detection

Zhaiming Shen, Menglun Wang, Guang Cheng +5

Being able to successfully determine whether the testing samples has similar distribution as the training samples is a fundamental question to address before we can safely deploy m…

cs.LG2024

Downstream Task-Oriented Generative Model Selections on Synthetic Data Training for Fraud Detection Models

Yinan Cheng, Chi-Hua Wang, Vamsi K. Potluru +2

Devising procedures for downstream task-oriented generative model selections is an unresolved problem of practical importance. Existing studies focused on the utility of a single f…

cs.LG2025

Risk In Context: Benchmarking Privacy Leakage of Foundation Models in Synthetic Tabular Data Generation

Jessup Byun, Xiaofeng Lin, Joshua Ward +1

Synthetic tabular data is essential for machine learning workflows, especially for expanding small or imbalanced datasets and enabling privacy-preserving data sharing. However, sta…

math.ST2020

Finite Time Analysis of Vector Autoregressive Models under Linear Restrictions

Yao Zheng, Guang Cheng

This paper develops a unified finite-time theory for the ordinary least squares estimation of possibly unstable and even slightly explosive vector autoregressive models under linea…

stat.ML2015

Stabilized Nearest Neighbor Classifier and Its Statistical Properties

Wei Sun, Xingye Qiao, Guang Cheng

The stability of statistical analysis is an important indicator for reproducibility, which is one main principle of scientific method. It entails that similar statistical conclusio…

cs.LG2024

Improve Fidelity and Utility of Synthetic Credit Card Transaction Time Series from Data-centric Perspective

Din-Yin Hsieh, Chi-Hua Wang, Guang Cheng

Exploring generative model training for synthetic tabular data, specifically in sequential contexts such as credit card transaction data, presents significant challenges. This pape…

stat.ML2021

Stein Neural Sampler

Tianyang Hu, Zixiang Chen, Hanxi Sun +3

We propose two novel samplers to generate high-quality samples from a given (un-normalized) probability density. Motivated by the success of generative adversarial networks, we con…

cs.NI2025

Drift-oriented Self-evolving Encrypted Traffic Application Classification for Actual Network Environment

Zihan Chen, Guang Cheng, Jinhui Li +3

Encrypted traffic classification technology is a crucial decision-making information source for network management and security protection. It has the advantages of excellent respo…

math.ST2014

Bootstrapping High Dimensional Time Series

Xianyang Zhang, Guang Cheng

This article studies bootstrap inference for high dimensional weakly dependent time series in a general framework of approximately linear statistics. The following high dimensional…

stat.ML2023

Ranking Differential Privacy

Shirong Xu, Will Wei Sun, Guang Cheng

Rankings are widely collected in various real-life scenarios, leading to the leakage of personal information such as users' preferences on videos or news. To protect rankings, exis…

math.ST2018

Nonparametric Testing under Random Projection

Meimei Liu, Zuofeng Shang, Guang Cheng

A common challenge in nonparametric inference is its high computational complexity when data volume is large. In this paper, we develop computationally efficient nonparametric test…

stat.ME2015

Active Clinical Trials for Personalized Medicine

Stanislav Minsker, Ying-Qi Zhao, Guang Cheng

Individualized treatment rules (ITRs) tailor treatments according to individual patient characteristics. They can significantly improve patient care and are thus becoming increasin…

cs.HC2022

Enhanced Nearest Neighbor Classification for Crowdsourcing

Jiexin Duan, Xingye Qiao, Guang Cheng

In machine learning, crowdsourcing is an economical way to label a large amount of data. However, the noise in the produced labels may deteriorate the accuracy of any classificatio…

stat.ML2022

Unlabeled Data Help: Minimax Analysis and Adversarial Robustness

Yue Xing, Qifan Song, Guang Cheng

The recent proposed self-supervised learning (SSL) approaches successfully demonstrate the great potential of supplementing learning algorithms with additional unlabeled data. Howe…

stat.ML2018

Statistical Optimality of Interpolated Nearest Neighbor Algorithms

Yue Xing, Qifan Song, Guang Cheng

In the era of deep learning, understanding over-fitting phenomenon becomes increasingly important. It is observed that carefully designed deep neural networks achieve small testing…

stat.ML2026

Training-Free Self-Correction for Multimodal Masked Diffusion Models

Yidong Ouyang, Panwen Hu, Zhengyan Wan +7

Masked diffusion models have emerged as a powerful framework for text and multimodal generation. However, their sampling procedure updates multiple tokens simultaneously and treats…

cs.LG2023

MissDiff: Training Diffusion Models on Tabular Data with Missing Values

Yidong Ouyang, Liyan Xie, Chongxuan Li +1

The diffusion model has shown remarkable performance in modeling data distributions and synthesizing data. However, the vanilla diffusion model requires complete or fully observed…

cs.LG2020

Directional Pruning of Deep Neural Networks

Shih-Kang Chao, Zhanyu Wang, Yue Xing +1

In the light of the fact that the stochastic gradient descent (SGD) often finds a flat minimum valley in the training loss, we propose a novel directional pruning method which sear…

stat.ML2025

Differentially Private Bootstrap: New Privacy Analysis and Inference Strategies

Zhanyu Wang, Guang Cheng, Jordan Awan

Differentially private (DP) mechanisms protect individual-level information by introducing randomness into the statistical analysis procedure. Despite the availability of numerous…

stat.ML2019

Bootstrapping Upper Confidence Bound

Botao Hao, Yasin Abbasi-Yadkori, Zheng Wen +1

Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confi…

physics.app-ph2017

Microstructure and properties of Cu-Sn-Zn-TiO2 Nano-composite coatings on mild steel

Weidong Gao, Di Cao, Yunxue Jin +3

Cu-Sn-Zn coatings have been widely used in industry for their unique properties, such as good conductivity, high corrosion resistance and excellent solderability. To further improv…

stat.ML2020

Online Batch Decision-Making with High-Dimensional Covariates

Chi-Hua Wang, Guang Cheng

We propose and investigate a class of new algorithms for sequential decision making that interacts with \textit{a batch of users} simultaneously instead of \textit{a user} at each…

stat.ML2020

Adversarially Robust Estimate and Risk Analysis in Linear Regression

Yue Xing, Ruizhi Zhang, Guang Cheng

Adversarially robust learning aims to design algorithms that are robust to small adversarial perturbations on input variables. Beyond the existing studies on the predictive perform…

math.ST2014

Efficient semiparametric estimation in generalized partially linear additive models for longitudinal/clustered data

Guang Cheng, Lan Zhou, Jianhua Z. Huang

We consider efficient estimation of the Euclidean parameters in a generalized partially linear additive models for longitudinal/clustered data when multiple covariates need to be m…

stat.ML2025

Utility Theory of Synthetic Data Generation

Shirong Xu, Will Wei Sun, Guang Cheng

Synthetic data algorithms are widely employed in industries to generate artificial data for downstream learning tasks. While existing research primarily focuses on empirically eval…

stat.ML2017

Stability Enhanced Large-Margin Classifier Selection

Will Wei Sun, Guang Cheng, Yufeng Liu

Stability is an important aspect of a classification procedure because unstable predictions can potentially reduce users' trust in a classification system and also harm the reprodu…

math.ST2015

Joint asymptotics for semi-nonparametric regression models with partially linear structure

Guang Cheng, Zuofeng Shang

We consider a joint asymptotic framework for studying semi-nonparametric regression models where (finite-dimensional) Euclidean parameters and (infinite-dimensional) functional par…

math.ST2018

Quadratic Discriminant Analysis under Moderate Dimension

Qing Yang, Guang Cheng

Quadratic discriminant analysis (QDA) is a simple method to classify a subject into two populations, and was proven to perform as well as the Bayes rule when the data dimension p i…

math.ST2017

Gaussian Approximation of General Nonparametric Posterior Distributions

Zuofeng Shang, Guang Cheng

In a general class of Bayesian nonparametric models, we prove that the posterior distribution can be asymptotically approximated by a Gaussian process. Our results apply to nonpara…

math.ST2018

High Dimensional Robust Inference for Cox Regression Models

Shengchun Kong, Zhuqing Yu, Xianyang Zhang +1

We consider high-dimensional inference for potentially misspecified Cox proportional hazard models based on low dimensional results by Lin and Wei [1989]. A de-sparsified Lasso est…

cs.LG2023

Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms

Ximing Li, Chendi Wang, Guang Cheng

Marginal-based methods achieve promising performance in the synthetic data competition hosted by the National Institute of Standards and Technology (NIST). To deal with high-dimens…

math.ST2013

Local and global asymptotic inference in smoothing spline models

Zuofeng Shang, Guang Cheng

This article studies local and global inference for smoothing spline estimation in a unified asymptotic framework. We first introduce a new technical tool called functional Bahadur…

cs.NI2025

PRIME: Plasticity-Robust Incremental Model for Encrypted Traffic Classification in Dynamic Network Environments

Tian Qin, Guang Cheng, Zihan Chen +1

With the continuous development of network environments and technologies, ensuring cyber security and governance is increasingly challenging. Network traffic classification(ETC) ca…

cs.AI2026

From Table to Cell: Attention for Better Reasoning with TABALIGN

Tung Sum Thomas Kwok, Zeyong Zhang, Xinyu Wang +6

Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constrain the planner to a left-to-…

cs.LG2024

Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models

Joshua Ward, Chi-Hua Wang, Guang Cheng

The promise of tabular generative models is to produce realistic synthetic data that can be shared and safely used without dangerous leakage of information from the training set. I…

stat.ME2022

Distributed Bootstrap for Simultaneous Inference Under High Dimensionality

Yang Yu, Shih-Kang Chao, Guang Cheng

We propose a distributed bootstrap method for simultaneous inference on high-dimensional massive data that are stored and processed with many machines. The method produces an $\ell…

math.ST2018

Early Stopping for Nonparametric Testing

Meimei Liu, Guang Cheng

Early stopping of iterative algorithms is an algorithmic regularization method to avoid over-fitting in estimation and classification. In this paper, we show that early stopping ca…

cs.NI2026

Treat Traffic Like Trees: A Semantic-Preserving Hierarchical Graph-Based Expert Framework for Encrypted Traffic Analysis

Yuantu Luo, Jun Tao, Linxiao Yu +1

Graph-based deep learning methods have been widely employed in encrypted traffic analysis to exploit latent correlations across different granularities. However, while complex prep…

cs.CL2025

Bridging the Language Gap: Synthetic Voice Diversity via Latent Mixup for Equitable Speech Recognition

Wesley Bian, Xiaofeng Lin, Guang Cheng

Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available trainin…

cs.LG2024

Dynamic Matching Bandit For Two-Sided Online Markets

Yuantong Li, Chi-hua Wang, Guang Cheng +1

Two-sided online matching platforms are employed in various markets. However, agents' preferences in the current market are usually implicit and unknown, thus needing to be learned…

math.ST2007

Convergence Rate of K-Step Maximum Likelihood Estimate in Semiparametric Models

Guang Cheng

We suggest an iterative approach to computing K-step maximum likelihood estimates (MLE) of the parametric components in semiparametric models based on their profile likelihoods. Th…

cs.LG2026

Privacy Auditing Synthetic Data Release through Local Likelihood Attacks

Joshua Ward, Chi-Hua Wang, Guang Cheng

Auditing the privacy leakage of synthetic data is an important but unresolved problem. Existing privacy auditing frameworks for synthetic data rely on heuristics and unrealistic as…

cs.CR2024

Watermarking Generative Categorical Data

Bochao Gu, Hengzhi He, Guang Cheng

In this paper, we propose a novel statistical framework for watermarking generative categorical data. Our method systematically embeds pre-agreed secret signals by splitting the da…

math.ST2007

The penalized profile sampler

Guang Cheng, Michael R. Kosorok

The penalized profile sampler for semiparametric inference is an extension of the profile sampler method (Lee, Kosorok and Fine, 2005) obtained by profiling a penalized log-likelih…

cs.LG2026

SYNTHONY: A Stress-Aware, Intent-Conditioned Agent for Deep Tabular Generative Models Selection

Hochan Son, Xiaofeng Lin, Jason Ni +1

Deep generative models for tabular data (GANs, diffusion models, and LLM-based generators) exhibit highly non-uniform behavior across datasets; the best-performing synthesizer fami…

math.ST2019

Nonparametric Bayesian Aggregation for Massive Data

Zuofeng Shang, Botao Hao, Guang Cheng

We develop a set of scalable Bayesian inference procedures for a general class of nonparametric regression models. Specifically, nonparametric Bayesian inferences are separately pe…

cond-mat.mtrl-sci2017

Influence of Bi addition on the property of Ag-Bi nano-composite coatings

Yuxin Wang, See Leng Tay, Xiaowei Zhou +3

Silver (Ag) coatings have been widely used in many industry areas due to their excellent conductivity. However, wider applications of Ag coatings have been hindered by their poor m…

stat.ML2026

Corrected Samplers for Discrete Flow Models

Zhengyan Wan, Yidong Ouyang, Liyan Xie +3

Discrete flow models (DFMs) have been proposed to learn the data distribution on finite state space, offering a flexible framework as an alternative to discrete diffusion models. A…

cs.DB2024

DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room

Tung Sum Thomas Kwok, Chi-hua Wang, Guang Cheng

Data collaboration via Data Clean Room offers value but raises privacy concerns, which can be addressed through synthetic data and multi-table synthesizers. Common multi-table synt…

math.ST2016

A Partially Linear Framework for Massive Heterogeneous Data

Tianqi Zhao, Guang Cheng, Han Liu

We consider a partially linear framework for modelling massive heterogeneous data. The major goal is to extract common features across all sub-populations while exploring heterogen…

math.ST2011

Bootstrap consistency for general semiparametric -estimation

Guang Cheng, Jianhua Z. Huang

Consider -estimation in a semiparametric model that is characterized by a Euclidean parameter of interest and an infinite-dimensional nuisance parameter. As a general purpose ap…

cs.CR2025

Breaking Distortion-free Watermarks in Large Language Models

Shayleen Reynolds, Hengzhi He, Dung Daniel T. Ngo +5

In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are gr…

stat.ML2019

Benefit of Interpolation in Nearest Neighbor Algorithms

Yue Xing, Qifan Song, Guang Cheng

The over-parameterized models attract much attention in the era of data science and deep learning. It is empirically observed that although these models, e.g. deep neural networks,…

math.ST2010

How Many Iterations are Sufficient for Semiparametric Estimation?

Guang Cheng

A common practice in obtaining a semiparametric efficient estimate is through iteratively maximizing the (penalized) log-likelihood w.r.t. its Euclidean parameter and functional nu…

math.ST2008

General frequentist properties of the posterior profile distribution

Guang Cheng, Michael R. Kosorok

In this paper, inference for the parametric component of a semiparametric model based on sampling from the posterior profile distribution is thoroughly investigated from the freque…

stat.ML2022

Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning

Pratik Ramprasad, Yuantong Li, Zhuoran Yang +3

The recent emergence of reinforcement learning has created a demand for robust statistical inference methods for the parameter estimates computed using these algorithms. Existing m…

stat.ML2019

Distributed Generalized Cross-Validation for Divide-and-Conquer Kernel Ridge Regression and its Asymptotic Optimality

Ganggang Xu, Zuofeng Shang, Guang Cheng

Tuning parameter selection is of critical importance for kernel ridge regression. To this date, data driven tuning method for divide-and-conquer kernel ridge regression (d-KRR) has…

cs.CR2026

SEAL-Tag: Self-Tag Evidence Aggregation with Probabilistic Circuits for PII-Safe Retrieval-Augmented Generation

Jin Xie, Songze Li, Guang Cheng

Retrieval-Augmented Generation (RAG) systems introduce a critical vulnerability: contextual leakage, where adversaries exploit instruction-following to exfiltrate Personally Identi…

cs.LG2026

When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation

Joshua Ward, Bochao Gu, Chi-Hua Wang +1

Large Language Models (LLMs) have recently demonstrated remarkable performance in generating high-quality tabular synthetic data. In practice, two primary approaches have emerged f…

cs.LG2024

Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data

Yue Xing, Xiaofeng Lin, Chenheng Xu +3

Large language models (LLMs) are powerful models that can learn concepts at the inference stage via in-context learning (ICL). While theoretical studies, e.g., \cite{zhang2023train…

cs.AI2026

REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces

Xiaofeng Lin, Yingxu Wang, Tung Sum Thomas Kwok +4

Large language model (LLM) agents now solve complex tasks through long plan-and-execution traces, yet the ability to locate errors in a completed traces still lags far behind, espe…

math.ST2020

Sparse and Low-rank Tensor Estimation via Cubic Sketchings

Botao Hao, Anru Zhang, Guang Cheng

In this paper, we propose a general framework for sparse and low-rank tensor estimation from cubic sketchings. A two-stage non-convex implementation is developed based on sparse te…

cs.LG2023

Improving Adversarial Robustness by Contrastive Guided Diffusion Process

Yidong Ouyang, Liyan Xie, Guang Cheng

Synthetic data generation has become an emerging tool to help improve the adversarial robustness in classification tasks since robust learning requires a significantly larger amoun…

math.ST2020

Moderate-Dimensional Inferences on Quadratic Functionals in Ordinary Least Squares

Xiao Guo, Guang Cheng

Statistical inferences for quadratic functionals of linear regression parameter have found wide applications including signal detection, global testing, inferences of error varianc…

math.ST2018

Distributed Nearest Neighbor Classification

Jiexin Duan, Xingye Qiao, Guang Cheng

Nearest neighbor is a popular nonparametric method for classification and regression with many appealing properties. In the big data era, the sheer volume and spatial/temporal disp…

stat.ML2026

Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework

Hengzhi He, Shirong Xu, Guang Cheng

Recent studies identified an intriguing phenomenon in recursive generative model training known as model collapse, where models trained on data generated by previous models exhibit…

cs.LG2022

Attention Enables Zero Approximation Error

Zhiying Fang, Yidong Ouyang, Ding-Xuan Zhou +1

Deep learning models have been widely applied in various aspects of daily life. Many variant models based on deep learning structures have achieved even better performances. Attent…

q-fin.TR2026

Arbitrage Analysis in Polymarket NBA Markets

Guang Cheng, Jiaxin Yang, Haoxuan Zou

While decentralized prediction markets like Polymarket have gained significant traction, their market microstructure and high-frequency pricing efficiency remain underexplored. Thi…

stat.ML2022

Federated Online Sparse Decision Making

Chi-Hua Wang, Wenjie Li, Guang Cheng +1

This paper presents a novel federated linear contextual bandits model, where individual clients face different K-armed stochastic bandits with high-dimensional decision context and…

stat.ML2020

Residual Bootstrap Exploration for Bandit Algorithms

Chi-Hua Wang, Yang Yu, Botao Hao +1

In this paper, we propose a novel perturbation-based exploration method in bandit algorithms with bounded or unbounded rewards, called residual bootstrap exploration (\texttt{ReBoo…

math.ST2015

Semiparametric Bernstein-von Mises Theorem: Second Order Studies

Yun Yang, Guang Cheng, David B. Dunson

The major goal of this paper is to study the second order frequentist properties of the marginal posterior distribution of the parametric component in semiparametric Bayesian model…

cs.CR2025

From Static to Adaptive Defense: Federated Multi-Agent Deep Reinforcement Learning-Driven Moving Target Defense Against DoS Attacks in UAV Swarm Networks

Yuyang Zhou, Guang Cheng, Kang Du +3

The proliferation of UAVs has enabled a wide range of mission-critical applications and is becoming a cornerstone of low-altitude networks, supporting smart cities, emergency respo…

stat.ML2020

Sharp Rate of Convergence for Deep Neural Network Classifiers under the Teacher-Student Setting

Tianyang Hu, Zuofeng Shang, Guang Cheng

Classifiers built with neural networks handle large-scale high dimensional data, such as facial images from computer vision, extremely well while traditional statistical methods of…

cs.AI2026

Enhancing Table Reasoning with Deterministic Table-State Rewards

Tung Sum Thomas Kwok, Xinyu Wang, Hengzhi He +9

Large Language Models (LLMs) struggle with multi-step reasoning over structured tables. The primary reason is the lack of explicit supervision for intermediate reasoning states. Ex…

cs.LG2026

Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching

Zhengyan Wan, Yidong Ouyang, Liyan Xie +3

Guidance provides a simple and effective framework for posterior sampling by steering the generation process towards the desired distribution. When modeling discrete data, existing…

cs.CR2026

Authenticated Contradictions from Desynchronized Provenance and Watermarking

Alexander Nemecek, Hengzhi He, Guang Cheng +1

Cryptographic provenance standards such as C2PA and invisible watermarking are positioned as complementary defenses for content authentication, yet the two verification layers are…

cs.CR2025

Toward Intelligent and Secure Cloud: Large Language Model Empowered Proactive Defense

Yuyang Zhou, Guang Cheng, Kang Du +2

The rapid evolution of cloud computing technologies and the increasing number of cloud applications have provided numerous benefits in our daily lives. However, the diversity and c…

stat.ML2021

Variance Reduction on General Adaptive Stochastic Mirror Descent

Wenjie Li, Zhanyu Wang, Yichen Zhang +1

In this work, we investigate the idea of variance reduction by studying its properties with general adaptive mirror descent algorithms in nonsmooth nonconvex finite-sum optimizatio…

stat.ML2026

Alignment of Diffusion Model and Flow Matching for Text-to-Image Generation

Yidong Ouyang, Liyan Xie, Hongyuan Zha +1

Diffusion models and flow matching have demonstrated remarkable success in text-to-image generation. While many existing alignment methods primarily focus on fine-tuning pre-traine…

math.ST2017

Computational Limits of A Distributed Algorithm For Smoothing Spline

Zuofeng Shang, Guang Cheng

In this paper, we explore statistical versus computational trade-off to address a basic question in the application of a distributed algorithm: what is the minimal computational co…

cs.LG2024

Decentralized Sparse Linear Regression via Gradient-Tracking: Linear Convergence and Statistical Guarantees

Marie Maros, Gesualdo Scutari, Ying Sun +1

We study sparse linear regression over a network of agents, modeled as an undirected graph and no server node. The estimation of the -sparse parameter is formulated as a constra…

stat.ML2024

Data Deletion for Linear Regression with Noisy SGD

Zhangjie Xia, Chi-Hua Wang, Guang Cheng

In the current era of big data and machine learning, it's essential to find ways to shrink the size of training dataset while preserving the training performance to improve efficie…

cs.LG2026

Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness

Lixing Zhang, Yidong Ouyang, Weifu Li +3

Missing value imputation is a fundamental task in machine learning, with most existing methods assuming that all missing entries correspond to unobserved regular values. In many re…

cs.CR2025

M3S-UPD: Efficient Multi-Stage Self-Supervised Learning for Fine-Grained Encrypted Traffic Classification with Unknown Pattern Discovery

Yali Yuan, Yu Huang, Xingjian Zeng +2

The growing complexity of encrypted network traffic presents dual challenges for modern network management: accurate multiclass classification of known applications and reliable de…

stat.ML2022

Benefit of Interpolation in Nearest Neighbor Algorithms

Yue Xing, Qifan Song, Guang Cheng

In some studies \citep[e.g.,][]{zhang2016understanding} of deep learning, it is observed that over-parametrized deep neural networks achieve a small testing error even when the tra…

stat.ML2019

A generalization of regularized dual averaging and its dynamics

Shih-Kang Chao, Guang Cheng

Excessive computational cost for learning large data and streaming data can be alleviated by using stochastic algorithms, such as stochastic gradient descent and its variants. Rece…

math.ST2008

Higher order semiparametric frequentist inference with the profile sampler

Guang Cheng, Michael R. Kosorok

We consider higher order frequentist inference for the parametric component of a semiparametric model based on sampling from the posterior profile distribution. The first order val…

cs.LG2023

Improve Deep Forest with Learnable Layerwise Augmentation Policy Schedule

Hongyu Zhu, Sichu Liang, Wentao Hu +4

As a modern ensemble technique, Deep Forest (DF) employs a cascading structure to construct deep models, providing stronger representational power compared to traditional decision…

cs.LG2024

Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective

Yue Xing, Xiaofeng Lin, Qifan Song +3

Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models. Existing literature, e.g., \cite{kim202…