Search

Your search keyword '"Gregory W. Wornell"' showing total 488 results
Start Over Author "Gregory W. Wornell"
488 results on '"Gregory W. Wornell"'

1. A Maximal Correlation Framework for Fair Machine Learning

Author

Joshua Lee, Yuheng Bu, Prasanna Sattigeri, Rameswar Panda, Gregory W. Wornell, Leonid Karlinsky, and Rogerio Schmidt Feris

Subjects
fairness, HGR maximal correlation, independence criterion, separation criterion, Science, Astrophysics, QB460-466, Physics, QC1-999
Abstract

As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore the problem of algorithmic fairness, taking an information–theoretic view. The maximal correlation framework is introduced for expressing fairness constraints and is shown to be capable of being used to derive regularizers that enforce independence and separation-based fairness criteria, which admit optimization algorithms for both discrete and continuous variables that are more computationally efficient than existing algorithms. We show that these algorithms provide smooth performance–fairness tradeoff curves and perform competitively with state-of-the-art methods on both discrete datasets (COMPAS, Adult) and continuous datasets (Communities and Crimes).

Published
2022
Full Text
View/download PDF

2. An Information Theoretic Interpretation to Deep Neural Networks

Author

Xiangxiang Xu, Shao-Lun Huang, Lizhong Zheng, and Gregory W. Wornell

Subjects
deep neural network, information theory, local information geometry, feature extraction, Science, Astrophysics, QB460-466, Physics, QC1-999
Abstract

With the unprecedented performance achieved by deep learning, it is commonly believed that deep neural networks (DNNs) attempt to extract informative features for learning tasks. To formalize this intuition, we apply the local information geometric analysis and establish an information-theoretic framework for feature selection, which demonstrates the information-theoretic optimality of DNN features. Moreover, we conduct a quantitative analysis to characterize the impact of network structure on the feature extraction process of DNNs. Our investigation naturally leads to a performance metric for evaluating the effectiveness of extracted features, called the H-score, which illustrates the connection between the practical training process of DNNs and the information-theoretic framework. Finally, we validate our theoretical results by experimental designs on synthesized data and the ImageNet dataset.

Published
2022
Full Text
View/download PDF

50. Asynchronous Massive Access and Neighbor Discovery Using OFDMA

Author

Xu Chen, Lina Liu, Dongning Guo, and Gregory W. Wornell

Subjects
FOS: Computer and information sciences, Computer Science - Information Theory, Information Theory (cs.IT), Library and Information Sciences, Computer Science Applications, Information Systems
Abstract

The fundamental communication problem in the wireless Internet of Things (IoT) is to discover a massive number of devices and to allow them reliable access to shared channels. Oftentimes these devices transmit short messages randomly and sporadically. This paper proposes a novel signaling scheme for grant-free massive access, where each device encodes its identity and/or information in a sparse set of tones. Such transmissions are implemented in the form of orthogonal frequency-division multiple access (OFDMA). Under some mild conditions and assuming device delays to be bounded unknown multiples of symbol intervals, sparse OFDMA is proved to enable arbitrarily reliable asynchronous device identification and message decoding with a codelength that is O(K(log K + log S + log N)), where N denotes the device population, K denotes the actual number of active devices, and log S is essentially equal to the number of bits a device can send (including its identity). By exploiting the Fast Fourier Transform (FFT), the computational complexity for discovery and decoding can be made to be sub-linear in the total device population. To prove the concept, a specific design is proposed to identify up to 100 active devices out of $2^{38}$ possible devices with up to 20 symbols of delay and moderate signal-to-noise ratios and fading. The codelength compares much more favorably with those of standard slotted ALOHA and carrier-sensing multiple access (CSMA) schemes.

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results