gradient-based training

5 papers

• AnaCP: Toward Upper-Bound Continual Learning via Analytic Contrastive Projection
• Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
• Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions
• From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
• Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws