29 citations · 158 across the 26 of their papers we have counts for
26 papers
Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models
Conlan Olson, Linjun Zhang, Zhun Deng +1
Individual fairness, the notion that "similar individuals should be treated similarly," provides a strong and flexible fairness guarantee for algorithmic decision makers. However,…
Provable Pluralistic Alignment: Multi-Party RLHF under Offline Human Feedback
Huiying Zhong, Zhun Deng, Tianwei Gao +3
Pluralistic alignment requires learning from feedback that reflects persistent and potentially conflicting stakeholder preferences while ultimately selecting a single collective po…
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
Yiyang Zhou, Chenhang Cui, Jaehong Yoon +5
Large vision-language models (LVLMs) have shown remarkable abilities in understanding visual information with human languages. However, LVLMs still suffer from object hallucination…
How Does Information Bottleneck Help Deep Learning?
Kenji Kawaguchi, Zhun Deng, Xu Ji +1
Numerous deep learning algorithms have been inspired by and understood via the notion of information bottleneck, where unnecessary information is (often implicitly) minimized while…
Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks
Yuzhen Mao, Zhun Deng, Huaxiu Yao +3
As machine learning has been deployed ubiquitously across applications in modern data science, algorithmic fairness has become a great concern. Among them, imposing fairness constr…
Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data
Ryumei Nakada, Halil Ibrahim Gulluk, Zhun Deng +3
Language-supervised vision models have recently attracted great attention in computer vision. A common approach to build such models is to use contrastive learning on paired data a…
HappyMap: A Generalized Multi-calibration Method
Zhun Deng, Cynthia Dwork, Linjun Zhang
Multi-calibration is a powerful and evolving concept originating in the field of algorithmic fairness. For a predictor that estimates the outcome given covariates , and…
Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions
Jake C. Snell, Thomas P. Zollo, Zhun Deng +2
Rigorous guarantees about the performance of predictive algorithms are necessary in order to ensure their responsible use. Previous work has largely focused on bounding the expecte…
Reinforcement Learning with Stepwise Fairness Constraints
Zhun Deng, He Sun, Zhiwei Steven Wu +2
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.…
Investigating Fairness Disparities in Peer Review: A Language Model Enhanced Approach
Jiayao Zhang, Hongming Zhang, Zhun Deng +1
Double-blind peer review mechanism has become the skeleton of academic research across multiple disciplines including computer science, yet several studies have questioned the qual…
FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data
Zhun Deng, Jiayao Zhang, Linjun Zhang +4
Algorithmic fairness plays an important role in machine learning and imposing fairness constraints during learning is a common approach. However, many datasets are imbalanced in ce…
Robustness Implies Generalization via Data-Dependent Generalization Bounds
Kenji Kawaguchi, Zhun Deng, Kyle Luh +1
This paper proves that robustness implies generalization via data-dependent generalization bounds. As a result, robustness and generalization are shown to be connected closely in a…
Scaffolding Sets
Maya Burhanpurkar, Zhun Deng, Cynthia Dwork +1
Predictors map individual instances in a population to the interval . For a collection of subsets of a population, a predictor is multi-calibrated with respect…
An Unconstrained Layer-Peeled Perspective on Neural Collapse
Wenlong Ji, Yiping Lu, Yiliang Zhang +2
Neural collapse is a highly symmetric geometric pattern of neural networks that emerges during the terminal phase of training, with profound implications on the generalization perf…
The Power of Contrast for Feature Learning: A Theoretical Analysis
Wenlong Ji, Zhun Deng, Ryumei Nakada +2
Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart. Despite its empirical succ…
Adversarial Training Helps Transfer Learning via Better Representations
Zhun Deng, Linjun Zhang, Kailas Vodrahalli +2
Transfer learning aims to leverage models pre-trained on source data to efficiently adapt to target setting, where only limited data are available for model fine-tuning. Recent wor…
Understanding Dynamics of Nonlinear Representation Learning and Its Application
Kenji Kawaguchi, Linjun Zhang, Zhun Deng
Representations of the world environment play a crucial role in artificial intelligence. It is often inefficient to conduct reasoning and inference directly in the space of raw sen…
When and How Mixup Improves Calibration
Linjun Zhang, Zhun Deng, Kenji Kawaguchi +1
In many machine learning applications, it is important for the model to provide confidence scores that accurately capture its prediction uncertainty. Although modern learning metho…
Towards Understanding the Dynamics of the First-Order Adversaries
Zhun Deng, Hangfeng He, Jiaoyang Huang +1
An acknowledged weakness of neural networks is their vulnerability to adversarial perturbations to the inputs. To improve the robustness of these models, one of the most popular de…
Interpreting Robust Optimization via Adversarial Influence Functions
Zhun Deng, Cynthia Dwork, Jialiang Wang +1
Robust optimization has been widely used in nowadays data science, especially in adversarial training. However, little research has been done to quantify how robust optimization ch…
Toward Better Generalization Bounds with Locally Elastic Stability
Zhun Deng, Hangfeng He, Weijie J. Su
Algorithmic stability is a key characteristic to ensure the generalization ability of a learning algorithm. Among different notions of stability, \emph{uniform stability} is arguab…
How Does Mixup Help With Robustness and Generalization?
Linjun Zhang, Zhun Deng, Kenji Kawaguchi +2
Mixup is a popular data augmentation technique based on taking convex combinations of pairs of examples and their labels. This simple technique has been shown to substantially impr…
Decision-Aware Conditional GANs for Time Series Data
He Sun, Zhun Deng, Hui Chen +1
We introduce the decision-aware time-series conditional generative adversarial network (DAT-CGAN) as a method for time-series generation. The framework adopts a multi-Wasserstein l…
Representation via Representations: Domain Generalization via Adversarially Learned Invariant Representations
Zhun Deng, Frances Ding, Cynthia Dwork +4
We investigate the power of censoring techniques, first developed for learning {\em fair representations}, to address domain generalization. We examine {\em adversarial} censoring…