Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Lipton, Zachary Chase"'
Autor:
Rohatgi, Dhruv, Marwah, Tanya, Lipton, Zachary Chase, Lu, Jianfeng, Moitra, Ankur, Risteski, Andrej
Graph neural networks (GNNs) are the dominant approach to solving machine learning problems defined over graphs. Despite much theoretical and empirical work in recent years, our understanding of finer-grained aspects of architectural design for GNNs
Externí odkaz:
http://arxiv.org/abs/2410.09867
Autor:
Garg, Saurabh, Setlur, Amrith, Lipton, Zachary Chase, Balakrishnan, Sivaraman, Smith, Virginia, Raghunathan, Aditi
Self-training and contrastive learning have emerged as leading techniques for incorporating unlabeled data, both under distribution shift (unsupervised domain adaptation) and when it is absent (semi-supervised learning). However, despite the populari
Externí odkaz:
http://arxiv.org/abs/2312.03318
Autor:
Baby, Dheeraj, Garg, Saurabh, Yen, Tzu-Ching, Balakrishnan, Sivaraman, Lipton, Zachary Chase, Wang, Yu-Xiang
This paper focuses on supervised and unsupervised online label shift, where the class marginals $Q(y)$ varies but the class-conditionals $Q(x|y)$ remain invariant. In the unsupervised setting, our goal is to adapt a learner, trained on some offline l
Externí odkaz:
http://arxiv.org/abs/2305.19570
Addressing such diverse ends as safety alignment with human preferences, and the efficiency of learning, a growing line of reinforcement learning research focuses on risk functionals that depend on the entire distribution of returns. Recent work on \
Externí odkaz:
http://arxiv.org/abs/2209.10444
Electronic records contain sequences of events, some of which take place all at once in a single visit, and others that are dispersed over multiple visits, each with a different timestamp. We postulate that fine temporal detail, e.g., whether a serie
Externí odkaz:
http://arxiv.org/abs/1904.12206
This paper provides new insight into maximizing F1 scores in the context of binary classification and also in the context of multilabel classification. The harmonic mean of precision and recall, F1 score is widely used to measure the success of a bin
Externí odkaz:
http://arxiv.org/abs/1402.1892
Autor:
Lipton, Zachary Chase
Publikováno v:
Lipton, Zachary Chase. (2017). Learning from Temporally-Structured Human Activities Data. UC San Diego: Computer Science. Retrieved from: http://www.escholarship.org/uc/item/6mw0q3j8
Despite the extraordinary success of deep learning on diverse problems, these triumphs are too often confined to large, clean datasets and well-defined objectives. Face recognition systems train on millions of perfectly annotated images. Commercial s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______325::422fdaee38483ff3df2e8793e802996e
http://www.escholarship.org/uc/item/6mw0q3j8
http://www.escholarship.org/uc/item/6mw0q3j8
Autor:
Aneni K; Child Study Center, Yale School of Medicine, New Haven, CT, United States.; Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, United States., Chen CH; Center for Computational Health, IBM Research, Yorktown Heights, NY, United States., Meyer J; Child Study Center, Yale School of Medicine, New Haven, CT, United States.; Fairfield University, Fairfield, CT, United States., Cho YT; Child Study Center, Yale School of Medicine, New Haven, CT, United States.; Department of Psychiatry, Yale School of Medicine, New Haven, CT, United States., Lipton ZC; Machine Learning Department, School of Computer Science, Carnegie Mellon University, Pittsburg, PA, United States., Kher S; Pomona College, Claremont, CA, United States., Jiao MG; McGovern Medical School, UTHealth Houston, Houston, TX, United States., Gomati de la Vega I; Pontificia Universidad Javeriana, Bogota, Colombia., Umutoni FA; Child Study Center, Yale School of Medicine, New Haven, CT, United States., McDougal RA; Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, United States.; Yale School of Public Health, New Haven, CT, United States., Fiellin LE; Child Study Center, Yale School of Medicine, New Haven, CT, United States.; Yale School of Public Health, New Haven, CT, United States.; Department of Internal Medicine, Yale School of Medicine, New Haven, CT, United States.
Publikováno v:
JMIR research protocols [JMIR Res Protoc] 2023 Nov 23; Vol. 12, pp. e46990. Date of Electronic Publication: 2023 Nov 23.
