scispace - formally typeset
Search or ask a question
Author

Michael I. Jordan

Other affiliations: Stanford University, Princeton University, Broad Institute  ...read more
Bio: Michael I. Jordan is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Inference. The author has an hindex of 176, co-authored 1016 publications receiving 216204 citations. Previous affiliations of Michael I. Jordan include Stanford University & Princeton University.


Papers
More filters
Journal ArticleDOI
TL;DR: In this article , a first-order optimization algorithm for bilinearly-coupled strongly-convex-concave minimax optimization called the AcceleratedGradient OptimisticGradient (AG-OG) was proposed.
Abstract: We provide a novel first-order optimization algorithm for bilinearly-coupled strongly-convex-concave minimax optimization called the AcceleratedGradient OptimisticGradient (AG-OG). The main idea of our algorithm is to leverage the structure of the considered minimax problem and operates Nesterov’s acceleration on the individual part and optimistic gradient on the coupling part of the objective. We motivate our method by showing that its continuous-time dynamics corresponds to an organic combination of the dynamics of optimistic gradient and of Nesterov’s acceleration. By discretizing the dynamics we conclude polynomial convergence behavior in discrete time. Further enhancement of AG-OG with proper restarting allows us to achieve rate-optimal (up to a constant) convergence rates with respect to the conditioning of the coupling and individual parts, which results in the first single-call algorithm achieving improved convergence in the deterministic setting and rate-optimality in the stochastic setting under bilinearly coupled minimax problem sets.

2 citations

Posted Content
TL;DR: In this paper, the authors study the problem of reinforcement learning in which the learner receives binary feedback only once at the end of an episode, and provide a statistically and computationally efficient algorithm that achieves sub-linear regret.
Abstract: We study a theory of reinforcement learning (RL) in which the learner receives binary feedback only once at the end of an episode. While this is an extreme test case for theory, it is also arguably more representative of real-world applications than the traditional requirement in RL practice that the learner receive feedback at every time step. Indeed, in many real-world applications of reinforcement learning, such as self-driving cars and robotics, it is easier to evaluate whether a learner's complete trajectory was either "good" or "bad," but harder to provide a reward signal at each step. To show that learning is possible in this more challenging setting, we study the case where trajectory labels are generated by an unknown parametric model, and provide a statistically and computationally efficient algorithm that achieves sub-linear regret.

2 citations

Posted Content
TL;DR: In this article, the authors introduce a relaxed notion of local exchangeability, where swapping data associated with nearby covariates causes a bounded change in the distribution and prove that locally exchangeable processes correspond to independent observations from an underlying measure-valued stochastic process.
Abstract: Exchangeability -- in which the distribution of an infinite sequence is invariant to reorderings of its elements -- implies the existence of a simple conditional independence structure that may be leveraged in the design of probabilistic models, efficient inference algorithms, and randomization-based testing procedures. In practice, however, this assumption is too strong an idealization; the distribution typically fails to be exactly invariant to permutations and de Finetti's representation theory does not apply. Thus there is the need for a distributional assumption that is both weak enough to hold in practice, and strong enough to guarantee a useful underlying representation. We introduce a relaxed notion of local exchangeability -- where swapping data associated with nearby covariates causes a bounded change in the distribution. We prove that locally exchangeable processes correspond to independent observations from an underlying measure-valued stochastic process. We thereby show that de Finetti's theorem is robust to perturbation and provide further justification for the Bayesian modelling approach. Using this probabilistic result, we develop three novel statistical procedures for (1) estimating the underlying process via local empirical measures, (2) testing via local randomization, and (3) estimating the canonical premetric of local exchangeability. These three procedures extend the applicability of previous exchangeability-based methods without sacrificing rigorous statistical guarantees. The paper concludes with examples of popular statistical models that exhibit local exchangeability.

2 citations

01 Sep 2017
TL;DR: This grant enabled the Berkeley Data Analytic System (BDAS) to implement significant portions of the code-bases, integrate BDAS with commonly used tools, and make BDAS much easier to manage.
Abstract: : The goal of this proposal was to deliver a modular open-source software stack that can support a new generation of large-scale analytic tools that provide answers over arbitrarily large datasets. This work was carried out by Berkeley's AMPLab, a research lab consisting of eleven faculty members and over 40 students. In addition to this grant, AMPLab (which ended in December 2016) was supported by industry affiliates and an NSF Expeditions grant. This grant was instrumental in improving our software stack, Berkeley Data Analytic System (BDAS), so that it can serve as a platform for the broader community. In particular, this grant enabled us to implement significant portions of the code-bases, integrate BDAS with commonly used tools, and make BDAS much easier to manage. In addition, it allowed us to extend the functionality of BDAS in several key area, including streaming, and query processing. Thanks to xData, BDAS has enjoyed a big success both in academia and industry. Today, Apache Spark is used by thousands of companies in production and counts over 400K meetup members worldwide, while Apache Mesos and Alluxio (formerly known as Tachyon) are used by hundreds of companies around the world.

2 citations

Proceedings Article
03 Jun 2020
TL;DR: A post-estimation smoothing operator is proposed as a fast and effective method for incorporating structural index data into prediction, which applies to a broad class of machine learning tasks, with no need to retrain models.
Abstract: Observational data are often accompanied by natural structural indices, such as time stamps or geographic locations, which are meaningful to prediction tasks but are often discarded We leverage semantically meaningful indexing data while ensuring robustness to potentially uninformative or misleading indices We propose a post-estimation smoothing operator as a fast and effective method for incorporating structural index data into prediction Because the smoothing step is separate from the original predictor, it applies to a broad class of machine learning tasks, with no need to retrain models Our theoretical analysis details simple conditions under which post-estimation smoothing will improve accuracy over that of the original predictor Our experiments on large scale spatial and temporal datasets highlight the speed and accuracy of post-estimation smoothing in practice Together, these results illuminate a novel way to consider and incorporate the natural structure of index variables in machine learning

2 citations


Cited by
More filters
Proceedings ArticleDOI
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

40,257 citations

Book
18 Nov 2016
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

38,208 citations

Book
01 Jan 1988
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Abstract: Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

37,989 citations

Journal ArticleDOI
TL;DR: This work proposes a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hofmann's aspect model.
Abstract: We describe latent Dirichlet allocation (LDA), a generative probabilistic model for collections of discrete data such as text corpora. LDA is a three-level hierarchical Bayesian model, in which each item of a collection is modeled as a finite mixture over an underlying set of topics. Each topic is, in turn, modeled as an infinite mixture over an underlying set of topic probabilities. In the context of text modeling, the topic probabilities provide an explicit representation of a document. We present efficient approximate inference techniques based on variational methods and an EM algorithm for empirical Bayes parameter estimation. We report results in document modeling, text classification, and collaborative filtering, comparing to a mixture of unigrams model and the probabilistic LSI model.

30,570 citations

Proceedings Article
03 Jan 2001
TL;DR: This paper proposed a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI).
Abstract: We propose a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams [6], and Hof-mann's aspect model, also known as probabilistic latent semantic indexing (pLSI) [3]. In the context of text modeling, our model posits that each document is generated as a mixture of topics, where the continuous-valued mixture proportions are distributed as a latent Dirichlet random variable. Inference and learning are carried out efficiently via variational algorithms. We present empirical results on applications of this model to problems in text modeling, collaborative filtering, and text classification.

25,546 citations