no code implementations • 14 Apr 2024 • Xiufan Yu, Linjun Zhang, Arun Srinivasan, Min-ge Xie, Lingzhou Xue
Compared to the existing $p$-value combination methods, including the vanilla Cauchy combination method, the proposed combination framework can handle the dependence accurately and utilizes the information efficiently to construct tests with accurate size and enhanced power.
1 code implementation • 2 Apr 2024 • Sai Li, Linjun Zhang
Machine learning methods often assume that the test data have the same distribution as the training data.
no code implementations • 22 Mar 2024 • Tianxi Cai, Feiqing Huang, Ryumei Nakada, Linjun Zhang, Doudou Zhou
To accommodate the statistical analysis of multimodal EHR data, in this paper, we propose a novel multimodal feature embedding generative model and design a multimodal contrastive loss to obtain the multimodal EHR feature representation.
no code implementations • 8 Mar 2024 • Huiying Zhong, Zhun Deng, Weijie J. Su, Zhiwei Steven Wu, Linjun Zhang
Our work \textit{initiates} the theoretical study of multi-party RLHF that explicitly models the diverse preferences of multiple individuals.
no code implementations • 25 Feb 2024 • Qichuan Yin, Junzhou Huang, Huaxiu Yao, Linjun Zhang
As federated learning gains increasing importance in real-world applications due to its capacity for decentralized data training, addressing fairness concerns across demographic groups becomes critically important.
no code implementations • 13 Feb 2024 • Zongbo Han, Yifeng Yang, Changqing Zhang, Linjun Zhang, Joey Tianyi Zhou, QinGhua Hu, Huaxiu Yao
The objective can be understood as seeking a model that fits the ground-truth labels by increasing the confidence while also maximizing the entropy of predicted probabilities by decreasing the confidence.
no code implementations • 16 Jan 2024 • Xintao Xia, Linjun Zhang, Zhanrui Cai
Privacy preservation has become a critical concern in high-dimensional data analysis due to the growing prevalence of data-driven applications.
no code implementations • 3 Jan 2024 • Haonan Wang, James Zou, Michael Mozer, Anirudh Goyal, Alex Lamb, Linjun Zhang, Weijie J Su, Zhun Deng, Michael Qizhe Xie, Hannah Brown, Kenji Kawaguchi
With the rise of advanced generative AI models capable of tasks once reserved for human creativity, the study of AI's creative potential becomes imperative for its responsible development and application.
1 code implementation • 6 Nov 2023 • Chenhang Cui, Yiyang Zhou, Xinyu Yang, Shirley Wu, Linjun Zhang, James Zou, Huaxiu Yao
To bridge this gap, we introduce a new benchmark, namely, the Bias and Interference Challenges in Visual Language Models (Bingo).
2 code implementations • 10 Oct 2023 • Jianguo Huang, Huajun Xi, Linjun Zhang, Huaxiu Yao, Yue Qiu, Hongxin Wei
In this paper, we empirically and theoretically show that disregarding the probabilities' value will mitigate the undesirable effect of miscalibrated probability values.
1 code implementation • 1 Oct 2023 • Yiyang Zhou, Chenhang Cui, Jaehong Yoon, Linjun Zhang, Zhun Deng, Chelsea Finn, Mohit Bansal, Huaxiu Yao
Large vision-language models (LVLMs) have shown remarkable abilities in understanding visual information with human languages.
1 code implementation • 18 Sep 2023 • Sai Li, Linjun Zhang
In conventional statistical and machine learning methods, it is typically assumed that the test data are identically distributed with the training data.
no code implementations • 6 Jul 2023 • Xinming Tu, James Zou, Weijie J. Su, Linjun Zhang
LLMs can also play a significant role in the classroom as interactive teaching and learning tools, contributing to personalized education.
1 code implementation • 13 Jun 2023 • Alyssa Huang, Peihan Liu, Ryumei Nakada, Linjun Zhang, Wanrong Zhang
The surge in multimodal AI's success has sparked concerns over data privacy in vision-and-language tasks.
1 code implementation • 1 May 2023 • Shirley Wu, Mert Yuksekgonul, Linjun Zhang, James Zou
Deep neural networks often rely on spurious correlations to make predictions, which hinders generalization beyond training environments.
no code implementations • 13 Mar 2023 • T. Tony Cai, Yichen Wang, Linjun Zhang
The score attack method is based on the tracing attack concept in differential privacy and can be applied to any statistical model with a well-defined score statistic.
no code implementations • 8 Mar 2023 • Zhun Deng, Cynthia Dwork, Linjun Zhang
Fairness is captured by incorporating demographic subgroups into the class of functions~$\mathcal{C}$.
1 code implementation • 13 Feb 2023 • Ryumei Nakada, Halil Ibrahim Gulluk, Zhun Deng, Wenlong Ji, James Zou, Linjun Zhang
We show that the algorithm can detect the ground-truth pairs and improve performance by fully exploiting unpaired datasets.
1 code implementation • 28 Nov 2022 • Puheng Li, James Zou, Linjun Zhang
Several group fairness notions and algorithms have been proposed.
no code implementations • 8 Nov 2022 • Zhun Deng, He Sun, Zhiwei Steven Wu, Linjun Zhang, David C. Parkes
AI methods are used in societally important settings, ranging from credit to employment to housing, and it is crucial to provide fairness in regard to algorithmic decision making.
1 code implementation • 20 Oct 2022 • Haotian Ye, James Zou, Linjun Zhang
This opens a promising strategy to first train a feature learner rather than a classifier, and then perform linear probing (last layer retraining) in the test environment.
1 code implementation • 11 Oct 2022 • Huaxiu Yao, Yiping Wang, Linjun Zhang, James Zou, Chelsea Finn
In this paper, we propose a simple yet powerful algorithm, C-Mixup, to improve generalization on regression tasks.
no code implementations • 6 Jun 2022 • Zhun Deng, Jiayao Zhang, Linjun Zhang, Ting Ye, Yates Coley, Weijie J. Su, James Zou
Specifically, FIFA encourages both classification and fairness generalization and can be flexibly combined with many existing fair learning methods with logits-based losses.
2 code implementations • 2 Jan 2022 • Huaxiu Yao, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, Chelsea Finn
Machine learning algorithms typically assume that training and test examples are drawn from the same distribution.
no code implementations • 4 Nov 2021 • Maya Burhanpurkar, Zhun Deng, Cynthia Dwork, Linjun Zhang
Predictors map individual instances in a population to the interval $[0, 1]$.
no code implementations • 6 Oct 2021 • Wenlong Ji, Zhun Deng, Ryumei Nakada, James Zou, Linjun Zhang
Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart.
no code implementations • 28 Jun 2021 • Kenji Kawaguchi, Linjun Zhang, Zhun Deng
Representation learning allows us to automatically discover suitable representations from raw sensory data.
no code implementations • NeurIPS 2021 • Zhun Deng, Linjun Zhang, Kailas Vodrahalli, Kenji Kawaguchi, James Zou
Recent works empirically demonstrate that adversarial training in the source data can improve the ability of models to transfer to new domains.
1 code implementation • ICLR 2022 • Huaxiu Yao, Linjun Zhang, Chelsea Finn
Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge.
no code implementations • 1 Apr 2021 • Zhe Zhang, Linjun Zhang
In this paper, we develop a general framework to design differentially private expectation-maximization (EM) algorithms in high-dimensional latent variable models, based on the noisy iterative hard-thresholding.
no code implementations • NeurIPS 2021 • Jinshuo Dong, Weijie J. Su, Linjun Zhang
The central question, therefore, is to understand which noise distribution optimizes the privacy-accuracy trade-off, especially when the dimension of the answer vector is high.
no code implementations • 11 Feb 2021 • Linjun Zhang, Zhun Deng, Kenji Kawaguchi, James Zou
In addition, we study how Mixup improves calibration in semi-supervised learning.
no code implementations • 8 Nov 2020 • T. Tony Cai, Yichen Wang, Linjun Zhang
We propose differentially private algorithms for parameter estimation in both low-dimensional and high-dimensional sparse generalized linear models (GLMs) by constructing private versions of projected gradient descent.
no code implementations • 6 Nov 2020 • Linjun Zhang, Rong Ma, T. Tony Cai, Hongzhe Li
Based on the iterative estimators, we further construct debiased estimators and establish their asymptotic normality.
no code implementations • ICLR 2021 • Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou
For robustness, we show that minimizing the Mixup loss corresponds to approximately minimizing an upper bound of the adversarial loss.
no code implementations • ICML 2020 • Zhun Deng, Cynthia Dwork, Jialiang Wang, Linjun Zhang
Robust optimization has been widely used in nowadays data science, especially in adversarial training.
no code implementations • 7 Sep 2020 • Jin Cao, Yibo Zhao, Linjun Zhang, Jason Li
The key to our approach is a computationally lightweight forward addition algorithm that we developed to recursively extract the functional dependencies between table columns that are scalable to tables with many columns.
1 code implementation • 26 Jul 2020 • Huaxiu Yao, Long-Kai Huang, Linjun Zhang, Ying WEI, Li Tian, James Zou, Junzhou Huang, Zhenhui Li
Moreover, both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets and are compatible with existing meta-learning algorithms.
no code implementations • 15 Jun 2020 • Zhun Deng, Linjun Zhang, Amirata Ghorbani, James Zou
In this work, we investigate how adversarial robustness can be enhanced by leveraging out-of-domain unlabeled data.
no code implementations • 12 Feb 2019 • T. Tony Cai, Yichen Wang, Linjun Zhang
By refining the "tracing adversary" technique for lower bounds in the theoretical computer science literature, we formulate a general lower bound argument for minimax risks with differential privacy constraints, and apply this argument to high-dimensional mean estimation and linear regression problems.
no code implementations • 16 Feb 2016 • T. Tony Cai, Linjun Zhang
We discuss a clustering method for Gaussian mixture model based on the sparse principal component analysis (SPCA) method and compare it with the IF-PCA method.