Srinadh Bhojanapalli

On the Reproducibility of Neural Network Predictions

2021 · arXiv (Cornell University)

Standard training techniques for neural networks involve multiple sources of randomness, e.g., initialization, mini-batch ordering and in some cases data augmentation. Given that neural networks are heavily over-parameterized in practice, such randomness can cause {\em …

Understanding Robustness of Transformers for Image Classification

2021 · arXiv (Cornell University)

Deep Convolutional Neural Networks (CNNs) have long been the architecture of choice for computer vision tasks. Recently, Transformer-based architectures like Vision Transformer (ViT) have matched or even surpassed ResNets for image classification. However, details of …