1.6k citations · 1.7k across the 9 of their papers we have counts for
5 papers · 1 filter
When does mixup promote local linearity in learned representations?
Arslan Chaudhry, Aditya Krishna Menon, Andreas Veit +3
Mixup is a regularization technique that artificially produces new samples using convex combinations of original training points. This simple technique has shown strong empirical p…
ELM: Embedding and Logit Margins for Long-Tail Learning
Wittawat Jitkrittum, Aditya Krishna Menon, Ankit Singh Rawat +1
Long-tail learning is the problem of learning under skewed label distributions, which pose a challenge for standard learners. Several recent approaches for the problem have propose…
Predicting on the Edge: Identifying Where a Larger Model Does Better
Taman Narayan, Heinrich Jiang, Sen Zhao +1
Much effort has been devoted to making large and more accurate models, but relatively little has been put into understanding which examples are benefiting from the added complexity…
Does label smoothing mitigate label noise?
Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon +1
Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing has been shown to im…
On the Convergence of Adam and Beyond
Sashank J. Reddi, Satyen Kale, Sanjiv Kumar
Several recently proposed stochastic optimization methods that have been successfully used in training deep networks such as RMSProp, Adam, Adadelta, Nadam are based on using gradi…