Deep Learning
Recursive Reinforcement Learning
These RL algorithms are designed with a flat Markovian view of the environment in the form of a "state, action, reward, and next state" interface [
A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective
Using the theoretical results, we provide a high-level understanding of how different design choices of MSDA work differently.
An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context
The inferred belief context can be leveraged to augment the state, leading to a policy that can adapt to abrupt variations in context.
SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance
However it often comes at a computational price which may hinder their deployment.
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis Wuyang Chen University of Texas at Austin Wei Huang
In this work, we theoretically characterize the impact of connectivity patterns on the convergence of DNNs under gradient descent training in fine granularity. By analyzing a wide network's Neural Network Gaussian Process (NNGP), we are able to depict how the spectrum of an