296 citations · 1.7k across the 43 of their papers we have counts for
6 papers · 1 filter
Leveraging redundancy in attention with Reuse Transformers
Srinadh Bhojanapalli, Ayan Chakrabarti, Andreas Veit +5
Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way, and is key to their success across diverse applications i…
Teacher's pet: understanding and mitigating biases in distillation
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon +1
Knowledge distillation is widely used as a means of improving the performance of a relatively simple student model using the predictions from a complex teacher model. Several works…
Eigen Analysis of Self-Attention and its Reconstruction from Partial Computation
Srinadh Bhojanapalli, Ayan Chakrabarti, Himanshu Jain +3
State-of-the-art transformer models use pairwise dot-product based self-attention, which comes at a computational cost quadratic in the input sequence length. In this paper, we inv…
A Simple and Effective Positional Encoding for Transformers
Pu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli +3
Transformer models are permutation equivariant. To supply the order and type information of the input tokens, position and segment embeddings are usually added to the input. Recent…
Understanding Robustness of Transformers for Image Classification
Srinadh Bhojanapalli, Ayan Chakrabarti, Daniel Glasner +3
Deep Convolutional Neural Networks (CNNs) have long been the architecture of choice for computer vision tasks. Recently, Transformer-based architectures like Vision Transformer (Vi…
On the Reproducibility of Neural Network Predictions
Srinadh Bhojanapalli, Kimberly Wilber, Andreas Veit +4
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 n…