On the Adaptivity of Stochastic Gradient-Based Optimization
Comments Accepted by SIAM Journal on Optimization; 54 pages
作者
Michael I. Jordan
Machine Learning
Online Learning Demands in Max-min Fairness
Optimal Mean Estimation without a Variance
Comments Fixed typographical errors in Theorem 1.2, Lemmas 4.3 and C.8
Stochastic Gradient and Langevin Processes
Comments ICML 2020, code available at https://github.com/dongyin92/noise_covariance
Do Offline Metrics Predict Online Performance in Recommender Systems?
Generalized Momentum-Based Methods: A Hamiltonian Perspective
Comments To appear in SIAM Journal on Optimization. v1 -> v2: minor edits + added funding acknowledgements, v2 -> v3: revised presentation, upon journal revision
Robust Optimization for Fairness with Noisy Protected Groups
Comments To appear at 34th Conference on Neural Information Processing Systems (NeurIPS 2020); first two authors contributed equally to this work
Transferable Calibration with Lower Bias and Variance in Domain Adaptation
On the Theory of Transfer Learning: The Importance of Task Diversity
Comments NeurIPS 2020
Decision-Making with Auto-Encoding Variational Bayes
Journal ref Advances in Neural Information Processing Systems 2020
Posterior Distribution for the Number of Clusters in Dirichlet Process Mixture Models
Exploration in two-stage recommender systems
Comments Published at the REVEAL 2020 workshop (RecSys 2020)
Improved Sample Complexity for Stochastic Compositional Variance Reduced Gradient
Comments 6 Pages. Accepted by ACC 2020
Asynchronous Online Testing of Multiple Hypotheses
Comments 36 pages, 16 figures
What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?
Comments This paper has been published at ICML2020. This new version made a correction to Proposition 19, and added more related works
On Localized Discrepancy for Domain Adaptation
Continuous-time Lower Bounds for Gradient-based Algorithms
Comments 13 pages
Covariance estimation with nonnegative partial correlations
Optimal Robust Linear Regression in Nearly Linear Time
Competing Bandits in Matching Markets
Comments 15 pages, 3 figures. A version appears in the Proceedings of The 23nd International Conference on Artificial Intelligence and Statistics (AISTATS), 2020
Finding Equilibrium in Multi-Agent Games with Payoff Uncertainty
Manifold Learning via Manifold Deflation
Sharp convergence rates for Langevin dynamics in the nonconvex setting
Comments 78 pages, 2 figures
Accelerated Message Passing for Entropy-Regularized MAP Inference
Active Learning for Nonlinear System Identification with Guarantees
Comments 29 pages
On Thompson Sampling with Langevin Algorithms
Fast Algorithms for Computational Optimal Transport and Wasserstein Barycenter
Comments 18 pages, 35 figures
Fundamental limits of detection in the spiked Wigner model
Comments Substantial text overlap with arXiv:1710.02903. This manuscript focuses on the LR fluctuations and the detection problem. The result is strengthened and the proof (execution of the interpolation and cavity methods) substantially simplified. Reflects more accurately the version to be published
Journal ref Ann. Statist., Volume 48, Number 2 (2020), 863-885
High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm
Comments Changes from v1: improved algorithm with $O (d^{1/4} / \varepsilon^{1/2})$ mixing time
