989 citations · 6.1k across the 184 of their papers we have counts for
8 papers · 1 filter
Coupled Recurrent Models for Polyphonic Music Composition
John Thickstun, Zaid Harchaoui, Dean P. Foster +1
This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music. We propose an efficient new conditional probabilistic fac…
Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Kendall Lowrey, Aravind Rajeswaran, Sham Kakade +2
We propose a plan online and learn offline (POLO) framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds…
Provably Correct Automatic Subdifferentiation for Qualified Programs
Sham Kakade, Jason D. Lee
The Cheap Gradient Principle (Griewank 2008) --- the computational cost of computing the gradient of a scalar-valued function is nearly the same (often within a factor of ) as t…
Stochastic subgradient method converges on tame functions
Damek Davis, Dmitriy Drusvyatskiy, Sham Kakade +1
This work considers the question: what convergence guarantees does the stochastic subgradient method have in the absence of smoothness and convexity? We prove that the stochastic s…
Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines
Cathy Wu, Aravind Rajeswaran, Yan Duan +5
Policy gradient methods have enjoyed great success in deep reinforcement learning but suffer from high variance of gradient estimates. The high variance problem is particularly exa…
On the insufficiency of existing momentum schemes for Stochastic Optimization
Rahul Kidambi, Praneeth Netrapalli, Prateek Jain +1
Momentum based stochastic gradient methods such as heavy ball (HB) and Nesterov's accelerated gradient descent (NAG) method are widely used in practice for training deep networks a…