作者
Michael I. Jordan
Machine Learning
Theoretically Principled Trade-off between Robustness and Accuracy
Comments Appeared in ICML 2019; the winning methodology of the NeurIPS 2018 Adversarial Vision Challenge
ML-LOO: Detecting Adversarial Examples with Feature Attribution
Non-convex Finite-Sum Optimization Via SCSG Methods
Comments Add Lemma B.1
Less than a Single Pass: Stochastically Controlled Stochastic Gradient Method
Comments Add Lemma B.4
Rao-Blackwellized Stochastic Gradients for Discrete Distributions
Comments Accepted to ICML 2019
A joint model of unpaired data from scRNA-seq and spatial transcriptomics for imputing missing gene expression measurements
Comments submitted to the 2019 ICML Workshop on Computational Biology
Decoding from Pooled Data: Sharp Information-Theoretic Bounds
Journal ref SIAM Journal on Mathematics of Data Science 1-1 (2019), pp. 161-188
LS-Tree: Model Interpretation When the Data Are Linguistic
A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm
On Finding Local Nash Equilibria (and Only Local Nash Equilibria) in Zero-Sum Games
Conditional Adversarial Domain Adaptation
Comments 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal, Canada
DAGGER: A sequential algorithm for FDR control on DAGs
Comments 29 pages, 10 figures, accepted for publication by Biometrika
Information Constraints on Auto-Encoding Variational Bayes
Journal ref Advances in Neural Information Processing Systems 31 (2018)
Probabilistic Multilevel Clustering via Composite Transportation Distance
Comments 25 pages, 3 figures
Kernel Feature Selection via Conditional Covariance Minimization
Comments The first two authors contributed equally
On the Local Minima of the Empirical Risk
Comments To appear in NIPS 2018
Covariances, Robustness, and Variational Bayes
CoCoA: A General Framework for Communication-Efficient Distributed Optimization
Ray: A Distributed Framework for Emerging AI Applications
Comments 17 pages, 14 figures, 13th USENIX Symposium on Operating Systems Design and Implementation, 2018
A Deep Generative Model for Semi-Supervised Classification with Noisy Labels
Comments accepted to BayLearn 2018
L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data
Is Q-learning Provably Efficient?
Comments Best paper in ICML 2018 workshop "Exploration in RL"
RLlib: Abstractions for Distributed Reinforcement Learning
Comments Published in the International Conference on Machine Learning (ICML 2018), 10 pages
Detection limits in the high-dimensional spiked rectangular model
Comments 28 pages. Appears in the proc. of the 31st annual Conference on Learning Theory (COLT) 2018
Learning to Explain: An Information-Theoretic Perspective on Model Interpretation
Comments Accepted to ICML 2018 as a long oral
Averaging Stochastic Gradient Descent on Riemannian Manifolds
Comments COLT 2018
Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data
Comments The first two authors contributed equally
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
A Lyapunov Analysis of Momentum Methods in Optimization
Comments Major revision. Cleaned up presentation and added results
