Lucas Liebenwein

Lucas Liebenwein

Auto-generated profile, based on publicly available information

Lucas Liebenwein

Massachusetts Institute of Technology, Cambridge, USA

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 November 2022 in Nature Machine Intelligence
Verified
Journal Article
Open access
PDF file
RHRamin Hasani
Ramin Hasani
MLMathias Lechner
Mathias Lechner
AAAlexander Amini
Alexander Amini
LLLucas Liebenwein
Lucas Liebenwein
ARAaron Ray
Aaron Ray
DRDaniela Rus
Daniela Rus
Continuous-time neural networks are a class of machine learning systems that can tackle representation learning on spatiotemporal decision-making tasks. These models are typically represented by continuous differential equations. However, their expressive power when they are deployed on computers is bottlenecked by numerical differential equation solvers. This limitation has notably slowed down the scaling and understanding of numerous natural physical phenomena such as the dynamics of nervous systems. Ideally, we would circumvent this bottleneck by solving the given dynamical system in closed form. This is known to be intractable in general. Here, we show that it is possible to closely approximate the interaction between neurons and synapses—the building blocks of natural and artificial neural networks—constructed by liquid time-constant networks efficiently in closed form. To this end, we compute a tightly bounded approximation of the solution of an integral appearing in liquid time-constant dynamics that has had no known closed-form solution so far. This closed-form solution impacts the design of continuous-time and continuous-depth neural models. For instance, since time appears explicitly in closed form, the formulation relaxes the need for complex numerical solvers. Consequently, we obtain models that are between one and five orders of magnitude faster in training and inference compared with differential equation-based counterparts. More importantly, in contrast to ordinary differential equation-based continuous networks, closed-form networks can scale remarkably well compared with other deep learning instances. Lastly, as these models are derived from liquid networks, they show good performance in time-series modelling compared with advanced recurrent neural network models.

26 June 2018
Verified
Conference Paper
Open access
LLLucas Liebenwein
Lucas Liebenwein
CBCenk Baykal
Cenk Baykal
IGIgor Gilitschenski
Igor Gilitschenski
SKSertac Karaman
Sertac Karaman
DRDaniela Rus
Daniela Rus

28 November 2019
Verified
Book Chapter
Open access
PDF file
LLLucas Liebenwein
Lucas Liebenwein
WSWilko Schwarting
Wilko Schwarting
CVCristian-Ioan Vasile
Cristian-Ioan Vasile
JDJonathan DeCastro
Jonathan DeCastro
JAJavier Alonso-Mora
Javier Alonso-Mora
DRDaniela Rus
Daniela Rus
Recent advances in autonomous driving have raised the problem of safety to the forefront and incentivized research into establishing safety guarantees. In this paper, we propose a safety verification framework as a safety standard for driving controllers with full or shared autonomy based on compositional and contract-based principles. Our framework enables us to synthesize safety guarantees over entire road networks by first building a library of locally verified models, and then composing local models together to verify the entire network. Composition is achieved using assume-guarantee contracts that are synthesized concurrently during verification. Thus, we can reuse local models within and across networks, add additional models to cover local road geometries without re-verifying the entire library, and perform all computations in a parallel and distributed way, which enables computational tractability. Furthermore, we employ controller contracts such that any controller satisfying them can be certified safe. We demonstrate the practical effectiveness of our framework by certifying controllers over parts of the Manhattan road network.

8 May 2020
Verified
Book Chapter
Closed access
PDF file
JDJonathan DeCastro
Jonathan DeCastro
LLLucas Liebenwein
Lucas Liebenwein
CVCristian-Ioan Vasile
Cristian-Ioan Vasile
RTRuss Tedrake
Russ Tedrake
SKSertac Karaman
Sertac Karaman
DRDaniela Rus
Daniela Rus

29 November 2022 in Nature Machine Intelligence
Verified
Journal Article
Open access
PDF file
RHRamin Hasani
Ramin Hasani
MLMathias Lechner
Mathias Lechner
AAAlexander Amini
Alexander Amini
LLLucas Liebenwein
Lucas Liebenwein
ARAaron Ray
Aaron Ray
DRDaniela Rus
Daniela Rus

4 March 2021 in arXiv
Verified
Preprint
Open access
PDF file
LLLucas Liebenwein
Lucas Liebenwein
CBCenk Baykal
Cenk Baykal
BCBrandon Carter
Brandon Carter
DGDavid Gifford
David Gifford
DRDaniela Rus
Daniela Rus
Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks. Starting from a pre-trained network, the process is as follows: remove redundant parameters, retrain, and repeat while maintaining the same test accuracy. The result is a model that is a fraction of the size of the original with comparable predictive performance (test accuracy). Here, we reassess and evaluate whether the use of test accuracy alone in the terminating condition is sufficient to ensure that the resulting model performs well across a wide spectrum of "harder" metrics such as generalization to out-of-distribution data and resilience to noise. Across evaluations on varying architectures and data sets, we find that pruned networks effectively approximate the unpruned model, however, the prune ratio at which pruned networks achieve commensurate performance varies significantly across tasks. These results call into question the extent of \emph{genuine} overparameterization in deep learning and raise concerns about the practicability of deploying pruned networks, specifically in the context of safety-critical systems, unless they are widely evaluated beyond test accuracy to reliably predict their performance. Our code is available at https://github.com/lucaslie/torchprune.