Brett W. Larsen

Publication Activity (10 Years)

Years Active: 2020-2024
Publications (10 Years): 15

Top Topics

Hausdorff Distance

Distributed Representations

Degrees Of Freedom

Shape Properties

Top Venues

SIAM J. Matrix Anal. Appl.

Publications

Cody Blakeney, Mansheej Paul, Brett W. Larsen, Sean Owen, Jonathan Frankle
Does your data spark joy? Performance gains from domain upsampling at the end of training. CoRR (2024)
Dean A. Pospisil, Brett W. Larsen, Sarah E. Harvey, Alex H. Williams
Estimating Shape Distances on Neural Representations with Limited Samples. ICLR (2024)
Mansheej Paul, Feng Chen, Brett W. Larsen, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? ICLR (2023)
Sarah E. Harvey, Brett W. Larsen, Alex H. Williams
Duality of Bures and Shape Distances with Implications for Comparing Neural Representations. CoRR (2023)
Dean A. Pospisil, Brett W. Larsen, Sarah E. Harvey, Alex H. Williams
Estimating Shape Distances on Neural Representations with Limited Samples. CoRR (2023)
Sarah E. Harvey, Brett W. Larsen, Alex H. Williams
Duality of Bures and Shape Distances with Implications for Comparing Neural Representations. UniReps (2023)
Brett W. Larsen, Tamara G. Kolda
Practical Leverage-Based Sampling for Low-Rank Tensor Decomposition. SIAM J. Matrix Anal. Appl. 43 (3) (2022)
Brett W. Larsen, Stanislav Fort, Nic Becker, Surya Ganguli
How many degrees of freedom do we need to train deep networks: a loss landscape perspective. ICLR (2022)
Mansheej Paul, Feng Chen, Brett W. Larsen, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask? CoRR (2022)
Brett W. Larsen, Shaul Druckmann
Towards a more general understanding of the algorithmic utility of recurrent connections. PLoS Comput. Biol. 18 (6) (2022)
Brett W. Larsen, Tamara G. Kolda
Sketching Matrix Least Squares via Leverage Scores Estimates. CoRR (2022)
Mansheej Paul, Brett W. Larsen, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks. CoRR (2022)
Mansheej Paul, Brett W. Larsen, Surya Ganguli, Jonathan Frankle, Gintare Karolina Dziugaite
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks. NeurIPS (2022)
Brett W. Larsen, Stanislav Fort, Nic Becker, Surya Ganguli
How many degrees of freedom do we need to train deep networks: a loss landscape perspective. CoRR (2021)
Brett W. Larsen, Tamara G. Kolda
Practical Leverage-Based Sampling for Low-Rank Tensor Decomposition. CoRR (2020)