R
Ruosong Wang
Researcher at Carnegie Mellon University
Publications - 74
Citations - 3376
Ruosong Wang is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Reinforcement learning & Function approximation. The author has an hindex of 21, co-authored 70 publications receiving 2340 citations. Previous affiliations of Ruosong Wang include Tsinghua University.
Papers
More filters
Proceedings Article
On Exact Computation with an Infinitely Wide Neural Net
TL;DR: The current paper gives the first efficient exact algorithm for computing the extension of NTK to convolutional neural nets, which it is called Convolutional NTK (CNTK), as well as an efficient GPU implementation of this algorithm.
Posted Content
Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks
TL;DR: This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and provides the following improvements over recent works: a tighter characterization of training speed, an explanation for why training a neuralNet with random labels leads to slower training, and a data-dependent complexity measure.
Proceedings Article
Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks
TL;DR: In this paper, a simple 2-layer ReLU network with random initialization is analyzed and generalization bound independent of network size is shown to be robust to the size of the network.
Posted Content
On Exact Computation with an Infinitely Wide Neural Net
TL;DR: In this paper, the authors presented an efficient exact algorithm for computing the extension of NTK to convolutional neural nets, which they call Convolutional NTK (CNTK), as well as an efficient GPU implementation of this algorithm.
Proceedings Article
Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning
TL;DR: For example, this article showed that even if the agent has a highly accurate linear representation, the agent still needs to sample an exponential number of trajectories in order to find a near-optimal policy.