88 citations · 176 across the 17 of their papers we have counts for
18 papers
Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via -Differential Privacy
Xiang Li, Buxin Su, Chendi Wang +2
Differentially private (DP) decentralized Federated Learning (FL) allows local users to collaborate without sharing their data with a central server. However, accurately quantifyin…
Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
Jiancong Xiao, Zhekun Shi, Kaizhao Liu +2
Despite its empirical success, Reinforcement Learning from Human Feedback (RLHF) has been shown to violate almost all the fundamental axioms in social choice theory -- such as majo…
Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts
Xiang Li, Garrett Wen, Weiqing He +3
Text watermarks in large language models (LLMs) are an increasingly important tool for detecting synthetic text and distinguishing human-written content from LLM-generated text. Wh…
Evaluating the Unseen Capabilities: How Many Theorems Do LLMs Know?
Xiang Li, Jiayi Xin, Qi Long +1
Accurate evaluation of large language models (LLMs) is crucial for understanding their capabilities and guiding their development. However, current evaluations often inconsistently…
Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching
Zhekun Shi, Kaizhao Liu, Qi Long +2
Nash Learning from Human Feedback is a game-theoretic framework for aligning large language models (LLMs) with human preferences by modeling learning as a two-player zero-sum game.…
Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium
Kaizhao Liu, Qi Long, Zhekun Shi +2
Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In thi…
Robust Detection of Watermarks for Large Language Models Under Human Edits
Xiang Li, Feng Ruan, Huiyuan Wang +2
Watermarking has offered an effective approach to distinguishing text generated by large language models (LLMs) from human-written text. However, the pervasive presence of human ed…
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization
Jiancong Xiao, Ziniu Li, Xingyu Xie +4
Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. Ho…
A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules
Xiang Li, Feng Ruan, Huiyuan Wang +2
Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking,…
Fair Canonical Correlation Analysis
Zhuoping Zhou, Davoud Ataee Tarzanagh, Bojian Hou +5
This paper investigates fairness and bias in Canonical Correlation Analysis (CCA), a widely used statistical technique for examining the relationship between two sets of variables.…
Multiple Imputation via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problems
Zongyu Dai, Zhiqi Bu, Qi Long
Missing data are present in most real world problems and need careful handling to preserve the prediction accuracy and statistical consistency in the downstream analysis. As the go…
Differentially Private Bayesian Neural Networks on Accuracy, Privacy and Reliability
Qiyiwen Zhang, Zhiqi Bu, Kan Chen +1
Bayesian neural network (BNN) allows for uncertainty quantification in prediction, offering an advantage over regular neural networks that has not been explored in the differential…
On the Convergence and Calibration of Deep Learning with Differential Privacy
Zhiqi Bu, Hua Wang, Zongyu Dai +1
Differentially private (DP) training preserves the data privacy usually at the cost of slower convergence (and thus lower accuracy), as well as more severe mis-calibration than its…
Minimax Estimation for Personalized Federated Learning: An Alternative between FedAvg and Local Training?
Shuxiao Chen, Qinqing Zheng, Qi Long +1
A widely recognized difficulty in federated learning arises from the statistical heterogeneity among clients: local datasets often originate from distinct yet not entirely unrelate…
Federated -Differential Privacy
Qinqing Zheng, Shuxiao Chen, Qi Long +1
Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information without compromising much on the privacy of their lo…
Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training
Cong Fang, Hangfeng He, Qi Long +1
In this paper, we introduce the \textit{Layer-Peeled Model}, a nonconvex yet analytically tractable optimization program, in a quest to better understand deep neural networks that…
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
Qinqing Zheng, Jinshuo Dong, Qi Long +1
Datasets containing sensitive information are often sequentially analyzed by many algorithms. This raises a fundamental question in differential privacy regarding how the overall p…
Deep Learning with Gaussian Differential Privacy
Zhiqi Bu, Jinshuo Dong, Qi Long +1
Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increas…