2 papers
cs.LG2024
Beyond Parameter Count: Implicit Bias in Soft Mixture of Experts
Youngseog Chung, Dhruv Malik, Jeff Schneider +2
The traditional viewpoint on Sparse Mixture of Experts (MoE) models is that instead of training a single large expert, which is computationally expensive, we can train many small e…
cs.LG2024
Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
Aakash Lahoti, Stefani Karp, Ezra Winston +2
Vision tasks are characterized by the properties of locality and translation invariance. The superior performance of convolutional neural networks (CNNs) on these tasks is widely a…