Similar Items: Reparameterized Complex-valued Neurons Can Efficiently Learn More than Real-valued Neurons via Gradient Descent
- Reparameterized Complex-valued Neurons Can Efficiently Learn More than Real-valued Neurons via Gradient Descent
- Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes
- CHANI: Correlation-based Hawkes Aggregation of Neurons with bio-Inspiration
- Optimization and Generalization of Gradient Descent for Shallow ReLU Networks with Minimal Width
- Litrepl: Literate Paper Processor Promoting Transparency More Than Reproducibility
- Computation by infinite descent made explicit