research Adam Convergence On Convergence of ADAM with Data Dependent Stepsize Compressed Fractional GD Fractional Gradient Descent with Matrix Stepsizes for Non-Convex Optimization LoRAE Learning Low-Rank Latent Spaces Using Simple Deterministic Autoencoders: Theoretical & Empirical Insights DIME DIME: Deterministic Information Maximizing Autoencoders