Optimization Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
The episode discusses a paper establishing population risk bounds for Kolmogorov-Arnold Networks (KANs) trained with Differentially Private Stochastic Gradient Descent (DP-SGD) using temporally correlated noise. Hosts discuss how this research provides concrete scaling rules for network width and training steps, improves privacy-utility trade-offs, and sets a foundation for designing robust AI systems under real-world noisy conditions.