18 citations · 46 across the 15 of their papers we have counts for
9 papers · 1 filter
Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
Michal Lukasik, Lin Chen, Harikrishna Narasimhan +7
Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal Area Under the ROC Curve (AUC) against a single bina…
It's an Alignment, Not a Trade-off: Revisiting Bias and Variance in Deep Models
Lin Chen, Michal Lukasik, Wittawat Jitkrittum +2
Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a \emph{trade-off}. However, in this…
What do larger image classifiers memorise?
Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat +2
The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well, despite being able to…
ResMem: Learn what you can and memorize the rest
Zitong Yang, Michal Lukasik, Vaishnavh Nagarajan +5
The impressive generalization performance of modern neural networks is attributed in part to their ability to implicitly memorize complex training patterns. Inspired by this, we ex…
Robust Distillation for Worst-class Performance
Serena Wang, Harikrishna Narasimhan, Yichen Zhou +3
Knowledge distillation has proven to be an effective technique in improving the performance a student model using predictions from a teacher model. However, recent work has shown t…
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…
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…