Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Ameet Talwalkar"'
Publikováno v:
American journal of human genetics, vol 109, iss 4
Inferring the structure of human populations from genetic variation data is a key task in population and medical genomic studies. Although a number of methods for population structure inference have been proposed, current methods are impractical to r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be976f26b962410b65b0f7ea54d1592e
https://doi.org/10.1016/j.ajhg.2022.02.015
https://doi.org/10.1016/j.ajhg.2022.02.015
Autor:
Ángel Alexander Cabrera, Erica Fu, Donald Bertucci, Kenneth Holstein, Ameet Talwalkar, Jason I. Hong, Adam Perer
Machine learning models with high accuracy on test data can still produce systematic failures, such as harmful biases and safety issues, when deployed in the real world. To detect and mitigate such failures, practitioners run behavioral evaluation of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::476c61f5b44634d365ff4245adeff4db
Autor:
Sen Lin, Ming Shi, Anish Arora, Raef Bassily, Elisa Bertino, Constantine Caramanis, Kaushik Chowdhury, Eylem Ekici, Atilla Eryilmaz, Stratis Ioannidis, Nan Jiang, Gauri Joshi, Jim Kurose, Yingbin Liang, Zhiqiang Lin, Jia Liu, Mingyan Liu, Tommaso Melodia, Aryan Mokhtari, Rob Nowak, Sewoong Oh, Srini Parthasarathy, Chunyi Peng, Hulya Seferoglu, Ness Shroff, Sanjay Shakkottai, Kannan Srinivasan, Ameet Talwalkar, Aylin Yener, Lei Ying
Publikováno v:
2022 IEEE 8th International Conference on Collaboration and Internet Computing (CIC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8c7d14257ba7d985736a10f1aee7b1f0
https://doi.org/10.1109/cic56439.2022.00013
https://doi.org/10.1109/cic56439.2022.00013
Advances in machine learning (ML) have enabled the development of next-generation prediction models for complex computational biology problems. These developments have spurred the use of interpretable machine learning (IML) to unveil fundamental biol
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2519eaee83dd905210e606f620ff43f9
https://doi.org/10.1101/2022.10.28.513978
https://doi.org/10.1101/2022.10.28.513978
Publikováno v:
Proc Mach Learn Res
A common workflow in data exploration is to learn a low-dimensional representation of the data, identify groups of points in that representation, and examine the differences between the groups to determine what they represent. We treat this workflow
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::5058de3e5016f380f4b55dfc7f381bcb
https://pubmed.ncbi.nlm.nih.gov/34532709
https://pubmed.ncbi.nlm.nih.gov/34532709
Inferring the structure of human populations from genetic variation data is a key task in population and medical genomic studies. While a number of methods for population structure inference have been proposed, current methods are impractical to run
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2280d79dc8f9f723717caf2a78145a48
https://doi.org/10.1101/2021.05.11.443705
https://doi.org/10.1101/2021.05.11.443705
Publikováno v:
ACSSC
Federated learning aims to jointly learn statistical models over massively distributed remote devices. In this work, we propose FedDANE, an optimization method that we adapt from DANE, a method for classical distributed optimization, to handle the pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3b661edf9b2c9e4d5d0acf9c8a9b6b19
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challeng
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4bd16a66418360115a325d42bc07490a
A new edition of a graduate-level machine learning textbook that focuses on the analysis and theory of algorithms.This book is a general introduction to machine learning that can serve as a textbook for graduate students and a reference for researche
Publikováno v:
CIKM
Industrial-scale machine learning applications often train and maintain massive models that can be on the order of hundreds of millions to billions of parameters. Model parallelism thus plays a significant role to support these machine learning tasks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3e3c17235b17f0a6ab49e324d693efc6
https://doi.org/10.1145/3132847.3132862
https://doi.org/10.1145/3132847.3132862