Publications

Conference Publications

*Equal contribution

2022

Unmasking the Lottery Ticket Hypothesis: What’s Encoded in a Winning Ticket’s Mask?
Mansheej Paul*, Feng Chen*, Brett W. Larsen*, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite
International Conference on Learning Representations (ICLR), 2023. Notable - Top 25%.

Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks
Mansheej Paul*, Brett W. Larsen*, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite
Advances in Neural Information Processing Systems (NeurIPS), 2022

2021

Deep Learning on a Data Diet: Finding Important Examples Early in Training
Mansheej Paul, Surya Ganguli, Gintare Karolina Dziugaite
Advances in Neural Information Processing Systems 34 (NeurIPS), 2021

2020

Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
Stanislav Fort*, Gintare Karolina Dziugaite*, Mansheej Paul, Sepideh Kharaghani, Daniel M. Roy, Surya Ganguli
Advances in Neural Information Processing Systems 33 (NeurIPS 2020)

Talks

  • MosaicML, October 2022

Peer-Reviewed Workshops

Unmasking the Lottery Ticket Hypothesis: Efficient Adaptive Pruning for Finding Winning Tickets
Mansheej Paul*, Feng Chen*, Brett W. Larsen*, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite
Poster at Has it Trained Yet? A Workshop for Algorithmic Efficiency in Practical Neural Network Training, Conference on Neural Information Processing Systems (NeurIPS), 2022

Pre-Training on a Data Diet: Identifying Sufficient Examples for Early Training
Mansheej Paul*, Brett W. Larsen*, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite
Poster at The First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward, International Conference on Machine Learning (ICML), 2022

Lottery Tickets on a Data Diet: Identifying Sufficient Data for Finding Sparse Trainable Networks
Mansheej Paul*, Brett W. Larsen*, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite  Spotlight at Sparsity in Neural Networks Workshop (SNN), 2022