↓Skip to main content

🏢 University of Basel

Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
·2952 words·14 mins· loading · loading
AI Theory Optimization 🏢 University of Basel
New theoretical bounds reveal how neural network architecture impacts the Gauss-Newton matrix’s conditioning, paving the way for improved optimization.
Loss Landscape Characterization of Neural Networks without Over-Parametrization
·2958 words·14 mins· loading · loading
AI Theory Optimization 🏢 University of Basel
Deep learning optimization is revolutionized by a new function class, enabling convergence guarantees without over-parameterization and accommodating saddle points.
A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
·2395 words·12 mins· loading · loading
AI Theory Generalization 🏢 University of Basel
This study provides a unified theory for kernel ridge regression’s learning curve, improving existing bounds and validating the Gaussian Equivalence Property under minimal assumptions.