Fangzhao Zhang

Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes

Spectral Adapter: Fine-Tuning in Spectral Space

Analyzing Neural Network Based Generative Diffusion Models via Convexification