1 citations · 1 across the 13 of their papers we have counts for
13 papers
Private Approximation of Graph Spectra and Cuts via Spectral Amplifiers
Chenglin Fan, Jingcheng Liu, Pan Peng +2
We study the problem of releasing a synthetic graph that approximates the sizes of all cuts of an input graph under edge-level differential privacy. If one insists on purely additi…
Finding Differentially Private Second Order Stationary Points in Stochastic Minimax Optimization
Difei Xu, Youming Tao, Meng Ding +2
We provide the first study of the problem of finding differentially private (DP) second-order stationary points (SOSP) in stochastic (non-convex) minimax optimization. Existing lit…
Learning-Augmented Ski Rental with Discrete Distributions: A Bayesian Approach
Bosun Kang, Hyejun Park, Chenglin Fan
We revisit the classic ski rental problem through the lens of Bayesian decision-making and machine-learned predictions. While traditional algorithms minimize worst-case cost withou…
Self-Critique-Guided Curiosity Refinement: Enhancing Honesty and Helpfulness in Large Language Models via In-Context Learning
Duc Hieu Ho, Chenglin Fan
Large language models (LLMs) have demonstrated robust capabilities across various natural language tasks. However, producing outputs that are consistently honest and helpful remain…
Learning Augmented Graph -Clustering
Chenglin Fan, Kijun Shin
Clustering is a fundamental task in unsupervised learning. Previous research has focused on learning-augmented -means in Euclidean metrics, limiting its applicability to complex…
Diffusion Models under Alternative Noise: Simplified Analysis and Sensitivity
Juhyeok Choi, Chenglin Fan
Diffusion models, typically formulated as discretizations of stochastic differential equations (SDEs), have achieved state-of-the-art performance in generative tasks. However, thei…
ACEvo: Adversarial Co-Evolution of Problem Distributions and Solvers for Combinatorial Optimization
Ruibo Duan, Yuxin Liu, Haoran Ye +3
Large language models (LLMs) are increasingly used to synthesize heuristic programs, yet most existing pipelines optimize solvers against fixed benchmark distributions. This static…
Verifiable Exponential Mechanism for Median Estimation
Hyukjun Kwon, Chenglin Fan
Differential Privacy (DP) is a rigorous privacy standard widely adopted in data analysis and machine learning. However, its guarantees rely on correctly introducing randomized nois…
A Generalized Binary Tree Mechanism for Differentially Private Approximation of All-Pair Distances
Michael Dinitz, Chenglin Fan, Jingcheng Liu +2
We study the problem of approximating all-pair distances in a weighted undirected graph with differential privacy, introduced by Sealfon [Sea16]. Given a publicly known undirected…
Inverse Materials Design by Large Language Model-Assisted Generative Framework
Yun Hao, Che Fan, Beilin Ye +7
Deep generative models hold great promise for inverse materials design, yet their efficiency and accuracy remain constrained by data scarcity and model architecture. Here, we intro…
Noise is All You Need: Private Second-Order Convergence of Noisy SGD
Dmitrii Avdiukhin, Michael Dinitz, Chenglin Fan +1
Private optimization is a topic of major interest in machine learning, with differentially private stochastic gradient descent (DP-SGD) playing a key role in both theory and practi…
Differentially Private Algorithms for Graph Cuts: A Shifting Mechanism Approach and More
Rishi Chandra, Michael Dinitz, Chenglin Fan +1
In this paper, we address the challenge of differential privacy in the context of graph cuts, specifically focusing on the multiway cut and the minimum -cut. We introduce edge-d…
Faster Algorithms for Generalized Mean Densest Subgraph Problem
Chenglin Fan, Ping Li, Hanyu Peng
The densest subgraph of a large graph usually refers to some subgraph with the highest average degree, which has been extended to the family of -means dense subgraph objectives…