Search Results for author:
Found 4 papers, 0 papers with code
Bridging the Gap: Addressing Discrepancies in Diffusion Model Training for Classifier-Free Guidance
Diffusion models have emerged as a pivotal advancement in generative models, setting new standards to the quality of the generated instances.
Multilayer Lookahead: a Nested Version of Lookahead
In recent years, SGD and its variants have become the standard tool to train Deep Neural Networks.
Implicit Gradient Alignment in Distributed and Federated Learning
A major obstacle to achieving global convergence in distributed and federated learning is the misalignment of gradients across clients, or mini-batches due to heterogeneity and stochasticity of the distributed data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
