Search Results for author:
Found 3 papers, 1 papers with code
Learning Low-Rank Latent Spaces with Simple Deterministic Autoencoder: Theoretical and Empirical Insights
In LoRAE, we incorporated a low-rank regularizer to adaptively reconstruct a low-dimensional latent space while preserving the basic objective of an autoencoder.
On the Contractivity of Plug-and-Play Operators
The present work is motivated by the following questions: Can we relax the assumptions on the forward model?
A Theoretical and Empirical Study on the Convergence of Adam with an "Exact" Constant Step Size in Non-Convex Settings
Lastly, (iii) we also demonstrate that our derived constant step size has better abilities in reducing the gradient norms, and empirically, we show that despite the accumulation of a few past gradients, the key driver for convergence in Adam is the non-increasing step sizes.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
