most citedHow Does Information Bottleneck Help Deep Learning?

15 citations · 22 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG20241 cited

Provable Multi-Party Reinforcement Learning with Diverse Human Feedback

Huiying Zhong, Zhun Deng, Weijie J. Su +2

Reinforcement learning with human feedback (RLHF) is an emerging paradigm to align models with human preferences. Typically, RLHF aggregates preferences from multiple individuals w…

cs.AI20246 cited

Can AI Be as Creative as Humans?

Haonan Wang, James Zou, Michael Mozer +8

Creativity serves as a cornerstone for societal progress and innovation. With the rise of advanced generative AI models capable of tasks once reserved for human creativity, the stu…

cs.AI2023

PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification

Qianli Shen, Wai Hoh Tang, Zhun Deng +2

Standard approaches for uncertainty quantification in deep learning and physics-informed learning have persistent limitations. Indicatively, strong assumptions regarding the data l…

cs.LG202315 cited

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…

cs.LG2023

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…

cs.LG2023

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…