wovepaper — the arXiv observatory

NewEvery arXiv paper, its researchers & institutions — mapped.

papers

Publications (17)

Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression

Sham Kakade, Adam Tauman Kalai, Varun Kanade +1

Learning from Logged Implicit Exploration Data

Alex Strehl, John Langford, Sham Kakade +1

Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines

Cathy Wu, Aravind Rajeswaran, Yan Duan +5

Domain Adaptation: Overfitting and Small Sample Statistics

Dean Foster, Sham Kakade, Ruslan Salakhutdinov

Online Meta-Learning

Chelsea Finn, Aravind Rajeswaran, Sham Kakade +1

Learning Overcomplete HMMs

Vatsal Sharan, Sham Kakade, Percy Liang +1

Prediction with a Short Memory

Vatsal Sharan, Sham Kakade, Percy Liang +1

A Linear Dynamical System Model for Text

David Belanger, Sham Kakade

Provably Correct Automatic Subdifferentiation for Qualified Programs

Sham Kakade, Jason D. Lee

An Optimal Algorithm for Linear Bandits

NicolÃ² Cesa-Bianchi, Sham Kakade

Stochastic subgradient method converges on tame functions

Damek Davis, Dmitriy Drusvyatskiy, Sham Kakade +1

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control

Kendall Lowrey, Aravind Rajeswaran, Sham Kakade +2

Leverage Score Sampling for Faster Accelerated Regression and ERM

Naman Agarwal, Sham Kakade, Rahul Kidambi +3

Minimal Realization Problems for Hidden Markov Models

Qingqing Huang, Rong Ge, Sham Kakade +1

(weak) Calibration is Computationally Hard

Elad Hazan, Sham Kakade

Learning Features of Music from Scratch

John Thickstun, Zaid Harchaoui, Sham Kakade

Convergence Rates of Active Learning for Maximum Likelihood Estimation

Kamalika Chaudhuri, Sham Kakade, Praneeth Netrapalli +1