Akhilan Boopathy

Fast Training of Provably Robust Neural Networks by SingleProp

2021 · arXiv (Cornell University)

Recent works have developed several methods of defending neural networks against adversarial attacks with certified guarantees. However, these techniques can be computationally costly due to the use of certification during training. We develop a new …

How to Train Your Wide Neural Network Without Backprop: An Input-Weight Alignment Perspective

2021 · arXiv (Cornell University)

Recent works have examined theoretical and empirical properties of wide neural networks trained in the Neural Tangent Kernel (NTK) regime. Given that biological neural networks are much wider than their artificial counterparts, we consider NTK …