Posteriors, conjugacy, and exponential families for completely random measures
Comments 42 pages
作者
Michael I. Jordan
Machine Learning
A constructive definition of the beta process
Perturbed Iterate Analysis for Asynchronous Stochastic Optimization
Comments 30 pages
Gradient Descent Converges to Minimizers
Comments Submitted to COLT 2016
Asymptotic behavior of $\ell_p$-based Laplacian regularization in semi-supervised learning
SparkNet: Training Deep Networks in Spark
Comments 12 pages, 7 figures
Optimal prediction for sparse linear models? Lower bounds for coordinate-separable M-estimators
Comments Add more coverage on related work; add a new lower bound for design matrices satisfying the restricted eigenvalue condition
Learning Halfspaces and Neural Networks with Random Initialization
Comments 31 pages
Asynchronous Complex Analytics in a Distributed Dataflow Architecture
$\ell_1$-regularized Neural Networks are Improperly Learnable in Polynomial Time
Comments 16 pages
Splash: User-friendly Programming Interface for Parallelizing Stochastic Algorithms
Comments redo experiments to learn bigger models; compare Splash with state-of-the-art implementations on Spark
Parallel Correlation Clustering on Big Graphs
Adding vs. Averaging in Distributed Primal-Dual Optimization
Comments ICML 2015: JMLR W&CP volume37, Proceedings of The 32nd International Conference on Machine Learning, pp. 1973-1982
On the accuracy of self-normalized log-linear models
Computational and Statistical Tradeoffs via Convex Relaxation
Variational consensus Monte Carlo
Evolutionary Inference via the Poisson Indel Process
Comments 33 pages, 6 figures
On the Computational Complexity of High-Dimensional Bayesian Variable Selection
Comments 42 pages, 3 figures
Learning Transferable Features with Deep Adaptation Networks
Bayesian Nonparametric Inference of Switching Linear Dynamical Systems
Comments 50 pages, 7 figures
The DLR Hierarchy of Approximate Inference
Comments Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005)
A sticky HDP-HMM with application to speaker diarization
Comments Published in at http://dx.doi.org/10.1214/10-AOAS395 the Annals of Applied Statistics (http://www.imstat.org/aoas/) by the Institute of Mathematical Statistics (http://www.imstat.org)
Journal ref Annals of Applied Statistics 2011, Vol. 5, No. 2A, 1020-1056
TuPAQ: An Efficient Planner for Large-scale Predictive Analytic Queries
Distributed Estimation of Generalized Matrix Rank: Efficient Algorithms and Lower Bounds
Comments 23 pages, 5 figures
Active Learning for Crowd-Sourced Databases
Comments A shorter version of this manuscript has been published in Proceedings of Very Large Data Bases 2015, entitled "Scaling Up Crowd-Sourcing to Very Large Datasets: A Case for Active Learning"
The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Velox
Joint modeling of multiple time series via the beta process with application to motion capture segmentation
Comments Published in at http://dx.doi.org/10.1214/14-AOAS742 the Annals of Applied Statistics (http://www.imstat.org/aoas/) by the Institute of Mathematical Statistics (http://www.imstat.org). arXiv admin note: text overlap with arXiv:1111.4226
Journal ref Annals of Applied Statistics 2014, Vol. 8, No. 3, 1281-1313
Spectral Methods meet EM: A Provably Optimal Algorithm for Crowdsourcing
Communication-Efficient Distributed Dual Coordinate Ascent
Comments NIPS 2014 version, including proofs. Published in Advances in Neural Information Processing Systems 27 (NIPS 2014)
Particle Gibbs with Ancestor Sampling
Journal ref Journal of Machine Learning Research, 15 (2014) 2145-2184
