M. I. Jordan
M. I. Jordan

homepage
jordanatcs.berkeley.edu

  Affiliation history
· Massachusetts Institute of Technology
· Center for Biological and Computational Learning, Cambridge
· University of California, Berkeley
Bibliometrics: publication history
Average citations per article51.12
Citation Count13,137
Publication count257
Publication years1986-2016
Available for download70
Average downloads per article1,084.14
Downloads (cumulative)75,890
Downloads (12 Months)5,417
Downloads (6 Weeks)696
ACM Fellow
SEARCH
ROLE
Arrow RightAuthor only
· Editor only
· Advisor only
· All roles


AUTHOR'S COLLEAGUES
See all colleagues of this author

SUBJECT AREAS
See all subject areas



AUTHOR PROFILE PAGES
Project background Author-Izer logoAuthor-Izer Service

BOOKMARK & SHARE


278 results found Export Results: bibtexendnote | acmref | csv

Result 1 – 20 of 278
Result page: 1 2 3 4 5 6 7 8 9 10 >>

Sort by:

1
Distributed optimization with arbitrary local solvers
Chenxin Ma, Jakub Konečný, Martin Jaggi, Virginia Smith, Michael I. Jordan, Peter Richtárik, Martin Takáč
July 2017 Optimization Methods & Software - The 17th British-French-German Conference on Optimization, 15-17 June 2015, London, United Kingdom: Volume 32 Issue 4, August 2017
Publisher: Taylor & Francis, Inc.
Bibliometrics:
Citation Count: 0

With the growth of data and necessity for distributed optimization methods, solvers that work well on a single machine must be re-designed to leverage distributed computation. Recent work in this area has been limited by focusing heavily on developing highly specific methods for the distributed environment. These special-purpose methods are ...
Keywords: machine learning, convergence analysis, distributed computing, primal-dual algorithm

2 published by ACM
Michael Jordan
June 2017 SIGMETRICS '17 Abstracts: Proceedings of the 2017 ACM SIGMETRICS / International Conference on Measurement and Modeling of Computer Systems
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 112,   Downloads (12 Months): 112,   Downloads (Overall): 112

Full text available: PDFPDF
Many new theoretical challenges have arisen in the area of gradient-based optimization for large-scale statistical data analysis, driven by the needs of applications and the opportunities provided by new hardware and software platforms. I discuss several recent results in this area, including: (1) a new framework for understanding Nesterov acceleration, ...
Keywords: gradient-based optimization, multiprocessor systems, nesterov acceleration

3 published by ACM
On Computational Thinking, Inferential Thinking and Data Science
Michael I. Jordan
July 2016 SPAA '16: Proceedings of the 28th ACM Symposium on Parallelism in Algorithms and Architectures
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 14,   Downloads (12 Months): 368,   Downloads (Overall): 368

Full text available: PDFPDF
The rapid growth in the size and scope of datasets in science and technology has created a need for novel foundational perspectives on data analysis that blend the inferential and computational sciences. That classical perspectives from these fields are not adequate to address emerging problems in "Big Data" is apparent ...
Keywords: big data, inference, parallelism, privacy, statistics, communication

4
l1-regularized neural networks are improperly learnable in polynomial time
Yuchen Zhang, Jason D. Lee, Michael I. Jordan
June 2016 ICML'16: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48
Publisher: JMLR.org
Bibliometrics:
Citation Count: 0

We study the improper learning of multi-layer neural networks. Suppose that the neural network to be learned has k hidden layers and that the l 1 -norm of the incoming weights of any neuron is bounded by L . We present a kernel-based method, such that with probability at least ...

5
A kernelized stein discrepancy for goodness-of-fit tests
Qiang Liu, Jason D. Lee, Michael Jordan
June 2016 ICML'16: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48
Publisher: JMLR.org
Bibliometrics:
Citation Count: 0

We derive a new discrepancy statistic for measuring differences between two probability distributions based on combining Stein's identity with the reproducing kernel Hilbert space theory. We apply our result to test how well a probabilistic model fits a set of observations, and derive a new class of powerful goodness-of-fit tests ...

6
The Constrained Laplacian Rank algorithm for graph-based clustering
Feiping Nie, Xiaoqian Wang, Michael I. Jordan, Heng Huang
February 2016 AAAI'16: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence
Publisher: AAAI Press
Bibliometrics:
Citation Count: 1

Graph-based clustering methods perform clustering on a fixed input data graph. If this initial construction is of low quality then the resulting clustering may also be of low quality. Moreover, existing graph-based clustering methods require post-processing on the data graph to extract the clustering indicators. We address both of these ...

7
Spectral methods meet EM: a provably optimal algorithm for crowdsourcing
Yuchen Zhang, Xi Chen, Dengyong Zhou, Michael I. Jordan
January 2016 The Journal of Machine Learning Research: Volume 17 Issue 1, January 2016
Publisher: JMLR.org
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 5,   Downloads (12 Months): 5,   Downloads (Overall): 5

Full text available: PDFPDF
Crowdsourcing is a popular paradigm for effectively collecting labels at low cost. The Dawid-Skene estimator has been widely used for inferring the true labels from the noisy labels provided by non-expert crowdsourcing workers. However, since the estimator maximizes a non-convex log-likelihood function, it is hard to theoretically justify its performance. ...
Keywords: spectral methods, EM, Dawid-Skene model, crowdsourcing, minimax rate, non-convex optimization

8
On the accuracy of self-normalized log-linear models
Jacob Andreas, Maxim Rabinovich, Michael I. Jordan, Dan Klein
December 2015 NIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems
Publisher: MIT Press
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 0,   Downloads (12 Months): 0,   Downloads (Overall): 0

Full text available: PDFPDF
Calculation of the log-normalizer is a major computational obstacle in applications of log-linear models with large output spaces. The problem of fast normalizer computation has therefore attracted significant attention in the theoretical and applied machine learning literature. In this paper, we analyze a recently proposed technique known as "self-normalization", which ...

9
Parallel correlation clustering on big graphs
Xinghao Pan, Dimitris Papailiopoulos, Samet Oymak, Benjamin Recht, Kannan Ramchandran, Michael I. Jordan
December 2015 NIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems
Publisher: MIT Press
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 0,   Downloads (12 Months): 0,   Downloads (Overall): 0

Full text available: PDFPDF
Given a similarity graph between items, correlation clustering (CC) groups similar items together and dissimilar ones apart. One of the most popular CC algorithms is KwikCluster : an algorithm that serially clusters neighborhoods of vertices, and obtains a 3-approximation ratio. Unfortunately, in practice KwikCluster requires a large number of clustering ...

10
Variational Consensus Monte Carlo
Maxim Rabinovich, Elaine Angelino, Michael I. Jordan
December 2015 NIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems
Publisher: MIT Press
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 1,   Downloads (12 Months): 1,   Downloads (Overall): 1

Full text available: PDFPDF
Practitioners of Bayesian statistics have long depended on Markov chain Monte Carlo (MCMC) to obtain samples from intractable posterior distributions. Unfortunately, MCMC algorithms are typically serial, and do not scale to the large datasets typical of modern machine learning. The recently proposed consensus Monte Carlo algorithm removes this limitation by ...

11
Linear response methods for accurate covariance estimates from Mean field variational Bayes
Ryan Giordano, Tamara Broderick, Michael Jordan
December 2015 NIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems
Publisher: MIT Press
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 0,   Downloads (12 Months): 0,   Downloads (Overall): 0

Full text available: PDFPDF
Mean field variational Bayes (MFVB) is a popular posterior approximation method due to its fast runtime on large-scale data sets. However, a well known major failing of MFVB is that it underestimates the uncertainty of model variables (sometimes severely) and provides no information about model variable covariance. We generalize linear ...

12 published by ACM
Evan R. Sparks, Ameet Talwalkar, Daniel Haas, Michael J. Franklin, Michael I. Jordan, Tim Kraska
August 2015 SoCC '15: Proceedings of the Sixth ACM Symposium on Cloud Computing
Publisher: ACM
Bibliometrics:
Citation Count: 4
Downloads (6 Weeks): 22,   Downloads (12 Months): 200,   Downloads (Overall): 577

Full text available: PDFPDF
The proliferation of massive datasets combined with the development of sophisticated analytical techniques has enabled a wide variety of novel applications such as improved product recommendations, automatic image tagging, and improved speech-driven interfaces. A major obstacle to supporting these predictive applications is the challenging and expensive process of identifying and ...

13
Distributed estimation of generalized matrix rank: efficient algorithms and lower bounds
Yuchen Zhang, Martin J. Wainwright, Michael I. Jordan
July 2015 ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37
Publisher: JMLR.org
Bibliometrics:
Citation Count: 0

We study the following generalized matrix rank estimation problem: given an n × n matrix and a constant c ≥ 0, estimate the number of eigenvalues that are greater than c. In the distributed setting, the matrix of interest is the sum of m matrices held by separate machines. We ...

14
Trust region policy optimization
John Schulman, Sergey Levine, Philipp Moritz, Michael Jordan, Pieter Abbeel
July 2015 ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37
Publisher: JMLR.org
Bibliometrics:
Citation Count: 0

In this article, we describe a method for optimizing control policies, with guaranteed monotonic improvement. By making several approximations to the theoretically-justified scheme, we develop a practical algorithm, called Trust Region Policy Optimization (TRPO). This algorithm is effective for optimizing large nonlinear policies such as neural networks. Our experiments demonstrate ...

15
Adding vs. averaging in distributed primal-dual optimization
Chenxin Ma, Virginia Smith, Martin Jaggi, Michael I. Jordan, Peter Richtárik, Martin Takáč
July 2015 ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37
Publisher: JMLR.org
Bibliometrics:
Citation Count: 0

Distributed optimization methods for large-scale machine learning suffer from a communication bottleneck. It is difficult to reduce this bottleneck while still efficiently and accurately aggregating partial work from different machines. In this paper, we present a novel generalization of the recent communication-efficient primal-dual framework (COCOA) for distributed optimization. Our framework, ...

16
Learning transferable features with deep adaptation networks
Mingsheng Long, Yue Cao, Jianmin Wang, Michael I. Jordan
July 2015 ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37
Publisher: JMLR.org
Bibliometrics:
Citation Count: 0

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Hence, it is important ...

17
A general analysis of the convergence of ADMM
Robert Nishihara, Laurent Lessard, Benjamin Recht, Andrew Packard, Michael I. Jordan
July 2015 ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37
Publisher: JMLR.org
Bibliometrics:
Citation Count: 0

We provide a new proof of the linear convergence of the alternating direction method of multipliers (ADMM) when one of the objective terms is strongly convex. Our proof is based on a framework for analyzing optimization algorithms introduced in Lessard et al. (2014), reducing algorithm convergence to verifying the stability ...

18 published by ACM
Christopher Ré, Divy Agrawal, Magdalena Balazinska, Michael Cafarella, Michael Jordan, Tim Kraska, Raghu Ramakrishnan
May 2015 SIGMOD '15: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data
Publisher: ACM
Bibliometrics:
Citation Count: 2
Downloads (6 Weeks): 16,   Downloads (12 Months): 159,   Downloads (Overall): 668

Full text available: PDFPDF
Machine learning seems to be eating the world with a new breed of high-value data-driven applications in image analysis, search, voice recognition, mobile, and office productivity products. To paraphrase Mike Stonebraker, machine learning is no longer a zero-billion-dollar business. As the home of high-value, data-driven applications for over four decades, ...
Keywords: database research, machine learning, panel

19 published by ACM
Computational Thinking, Inferential Thinking and "Big Data"
Michael I. Jordan
May 2015 PODS '15: Proceedings of the 34th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems
Publisher: ACM
Bibliometrics:
Citation Count: 0
Downloads (6 Weeks): 5,   Downloads (12 Months): 105,   Downloads (Overall): 609

Full text available: PDFPDF
The phenomenon of "Big Data" is creating a need for research perspectives that blend computational thinking (with its focus on, e.g., abstractions, algorithms and scalability) with inferential thinking (with its focus on, e.g., underlying populations, sampling patterns, error bars and predictions). Database researchers and statistical machine learning researchers are centrally ...
Keywords: inferential thinking, big data, statistical machine learning, computational thinking

20
Distributed matrix completion and robust factorization
Lester Mackey, Ameet Talwalkar, Michael I. Jordan
January 2015 The Journal of Machine Learning Research: Volume 16 Issue 1, January 2015
Publisher: JMLR.org
Bibliometrics:
Citation Count: 1
Downloads (6 Weeks): 5,   Downloads (12 Months): 42,   Downloads (Overall): 72

Full text available: PDFPDF
If learning methods are to scale to the massive sizes of modern data sets, it is essential for the field of machine learning to embrace parallel and distributed computing. Inspired by the recent development of matrix factorization methods with rich theory but poor computational complexity and by the relative ease ...
Keywords: matrix factorization, video surveillance, collaborative filtering, parallel and distributed algorithms, randomized algorithms, robust matrix factorization, divide-and-conquer, matrix completion



The ACM Digital Library is published by the Association for Computing Machinery. Copyright © 2017 ACM, Inc.
Terms of Usage   Privacy Policy   Code of Ethics   Contact Us