activity
20132021
most citedOn the Reproducibility of Neural Network Predictions

17 citations · 37 across the 5 of their papers we have counts for

collaborators

8 papers

cs.LG2021

Balancing Robustness and Sensitivity using Feature Contrastive Learning

Seungyeon Kim, Daniel Glasner, Srikumar Ramalingam +3

It is generally believed that robust training of extremely large networks is critical to their success in real-world applications. However, when taken to the extreme, methods that…

cs.LG202117 cited

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…

cs.CL2020

Semantic Label Smoothing for Sequence to Sequence Problems

Michal Lukasik, Himanshu Jain, Aditya Krishna Menon +4

Label smoothing has been shown to be an effective regularization strategy in classification, that prevents overfitting and helps in label de-noising. However, extending such method…

cs.LG2020

Evaluations and Methods for Explanation through Robustness Analysis

Cheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu +4

Feature based explanations, that provide importance of each feature towards the model prediction, is arguably one of the most intuitive ways to explain a model. In this paper, we e…

cs.LG202016 cited

Why distillation helps: a statistical perspective

Aditya Krishna Menon, Ankit Singh Rawat, Sashank J. Reddi +2

Knowledge distillation is a technique for improving the performance of a simple "student" model by replacing its one-hot training labels with a distribution over labels obtained fr…

math.OC2019

Why are Adaptive Methods Good for Attention Models?

Jingzhao Zhang, Sai Praneeth Karimireddy, Andreas Veit +4

While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across…