Follow
Lucas Liebenwein
Title
Cited by
Cited by
Year
Provable Filter Pruning for Efficient Neural Networks
L Liebenwein*, C Baykal*, H Lang, D Feldman, D Rus
International Conference on Learning Representations, 2020
642020
Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds
C Baykal*, L Liebenwein*, I Gilitschenski, D Feldman, D Rus
International Conference on Learning Representations, 2019
572019
Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy
L Liebenwein, C Baykal, B Carter, D Gifford, D Rus
Proceedings of Machine Learning and Systems (MLSys 2021), 2021
192021
Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space
W Schwarting*, T Seyde*, I Gilitschenski*, L Liebenwein, R Sander, ...
Conference on Robot Learning (CoRL), 2020
172020
Sampling-Based Approximation Algorithms for Reachability Analysis with Provable Guarantees
L Liebenwein*, C Baykal*, I Gilitschenski, S Karaman, D Rus
Robotics: Science and Systems XIV (RSS), 2018
172018
SiPPing Neural Networks: Sensitivity-informed Provable Pruning of Neural Networks
C Baykal*, L Liebenwein*, I Gilitschenski, D Feldman, D Rus
arXiv preprint arXiv:1910.05422, 2019
142019
Compositional and Contract-based Verification for Autonomous Driving on Road Networks
L Liebenwein, W Schwarting, CI Vasile, J DeCastro, J Alonso-Mora, ...
Robotics Research: The 18th International Symposium ISRR, 2018
132018
Machine Learning-based Estimation of Forest Carbon Stocks to increase Transparency of Forest Preservation Efforts
B Lütjens, L Liebenwein, K Kramer
arXiv preprint arXiv:1912.07850, 2019
122019
Counterexample-guided safety contracts for autonomous driving
J DeCastro*, L Liebenwein*, CI Vasile, R Tedrake, S Karaman, D Rus
International Workshop on the Algorithmic Foundations of Robotics, 2018
92018
Closed-form Continuous-Depth Models
R Hasani, M Lechner, A Amini, L Liebenwein, M Tschaikowski, G Teschl, ...
arXiv preprint arXiv:2106.13898, 2021
72021
Sparse flows: Pruning continuous-depth models
L Liebenwein, R Hasani, A Amini, D Rus
Advances in Neural Information Processing Systems 34, 2021
52021
Training Support Vector Machines using Coresets
C Baykal, L Liebenwein, W Schwarting
arXiv preprint arXiv:1708.03835, 2017
52017
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
L Liebenwein, A Maalouf, D Feldman, D Rus
Advances in Neural Information Processing Systems 34, 2021
32021
Sensitivity-Informed Provable Pruning of Neural Networks
C Baykal, L Liebenwein, I Gilitschenski, D Feldman, D Rus
SIAM Journal on Mathematics of Data Science 4 (1), 26-45, 2022
22022
Low-Regret Active learning
C Baykal, L Liebenwein, D Feldman, D Rus
arXiv preprint arXiv:2104.02822, 2021
12021
End-to-End Sensitivity-Based Filter Pruning
Z Babaiee, L Liebenwein, R Hasani, D Rus, R Grosu
arXiv preprint arXiv:2204.07412, 2022
2022
Efficient Deep Learning: From Theory to Practice
L Liebenwein
Massachusetts Institute of Technology, 2021
2021
SYSTEM AND METHOD OF VALIDATION OF OPERATIONAL REGULATIONS TO AUTONOMOUSLY OPERATE A VEHICLE DURING TRAVEL
J Decastro, L Liebenwein, C Vasile, RL Tedrake, S Karaman, D Rus
US Patent App. 16/539,772, 2020
2020
Contract-based safety verification for autonomous driving
L Liebenwein
Massachusetts Institute of Technology, 2018
2018
Supplementary Material:“Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition”
L Liebenwein, A Maalouf, D Feldman, D Rus
The system can't perform the operation now. Try again later.
Articles 1–20