3k citations · 24.2k across the 299 of their papers we have counts for
12 papers · 2 filters
Gen-Oja: A Two-time-scale approach for Streaming CCA
Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion +2
In this paper, we study the problems of principal Generalized Eigenvector computation and Canonical Correlation Analysis in the stochastic setting. We propose a simple and efficien…
Probabilistic Multilevel Clustering via Composite Transportation Distance
Nhat Ho, Viet Huynh, Dinh Phung +1
We propose a novel probabilistic approach to multilevel clustering problems based on composite transportation distance, which is a variant of transportation distance where the unde…
A Deep Generative Model for Semi-Supervised Classification with Noisy Labels
Maxime Langevin, Edouard Mehlman, Jeffrey Regier +3
Class labels are often imperfectly observed, due to mistakes and to genuine ambiguity among classes. We propose a new semi-supervised deep generative model that explicitly models n…
L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data
Jianbo Chen, Le Song, Martin J. Wainwright +1
We study instancewise feature importance scoring as a method for model interpretation. Any such method yields, for each predicted instance, a vector of importance scores associated…
Is Q-learning Provably Efficient?
Chi Jin, Zeyuan Allen-Zhu, Sebastien Bubeck +1
Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. The…
Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Data
Puyudi Yang, Jianbo Chen, Cho-Jui Hsieh +2
We present a probabilistic framework for studying adversarial attacks on discrete data. Based on this framework, we derive a perturbation-based method, Greedy Attack, and a scalabl…
Information Constraints on Auto-Encoding Variational Bayes
Romain Lopez, Jeffrey Regier, Michael I. Jordan +1
Parameterizing the approximate posterior of a generative model with neural networks has become a common theme in recent machine learning research. While providing appealing flexibi…
On the Local Minima of the Empirical Risk
Chi Jin, Lydia T. Liu, Rong Ge +1
Population risk is always of primary interest in machine learning; however, learning algorithms only have access to the empirical risk. Even for applications with nonconvex nonsmoo…
Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning
Vladimir Feinberg, Alvin Wan, Ion Stoica +3
Recent model-free reinforcement learning algorithms have proposed incorporating learned dynamics models as a source of additional data with the intention of reducing sample complex…
Averaging Stochastic Gradient Descent on Riemannian Manifolds
Nilesh Tripuraneni, Nicolas Flammarion, Francis Bach +1
We consider the minimization of a function defined on a Riemannian manifold accessible only through unbiased estimates of its gradients. We develop a geometric framew…
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
Max Simchowitz, Horia Mania, Stephen Tu +2
We prove that the ordinary least-squares (OLS) estimator attains nearly minimax optimal performance for the identification of linear dynamical systems from a single observed trajec…
Learning to Explain: An Information-Theoretic Perspective on Model Interpretation
Jianbo Chen, Le Song, Martin J. Wainwright +1
We introduce instancewise feature selection as a methodology for model interpretation. Our method is based on learning a function to extract a subset of features that are most info…