Antonio Orvieto

6 papers ELLIS Institute Tübingen, MPI-IS

• Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size
• Fixed-Point RNNs: Interpolating from Diagonal to Dense
• Generalized Linear Mode Connectivity for Transformers
• Generalized Linear Mode Connectivity for Transformers
• In Search of Adam’s Secret Sauce
• In Search of Adam’s Secret Sauce