REVIEW 3 cited by
Regularisation of Neural Networks by Enforcing Lipschitz Continuity
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
We investigate the effect of explicitly enforcing the Lipschitz continuity of neural networks with respect to their inputs. To this end, we provide a simple technique for computing an upper bound to the Lipschitz constant---for multiple $p$-norms---of a feed forward neural network composed of commonly used layer types. Our technique is then used to formulate training a neural network with a bounded Lipschitz constant as a constrained optimisation problem that can be solved using projected stochastic gradient methods. Our evaluation study shows that the performance of the resulting models exceeds that of models trained with other common regularisers. We also provide evidence that the hyperparameters are intuitive to tune, demonstrate how the choice of norm for computing the Lipschitz constant impacts the resulting model, and show that the performance gains provided by our method are particularly noticeable when only a small amount of training data is available.
Forward citations
Cited by 3 Pith papers
-
Bridging Adaptivity and Safety: Learning Agile Collision-Free Locomotion Across Varied Physics
A legged-robot controller that estimates payload and friction online and uses those estimates to switch between agile and recovery policies achieves lower collision rates and higher speeds than non-adaptive baselines.
-
Generating Bearing Vibration Signals at User-Specified Fault Probabilities Using PR-GAN and Counterfactual Methods
Per-sample counterfactual optimization steers a fixed ensemble classifier's fault probability to arbitrary targets on CWRU/Paderborn vibration windows with ~0.005 error, outperforming a probability-regularized WGAN.
-
Robust Optimal Safe and Stability Guaranteeing Reinforcement Learning Control for Quadcopter
The authors apply a Lipschitz-bounded reinforcement learning controller to a quadcopter, claiming robust asymptotic stability with a certified safe domain under parametric uncertainty.
Discussion (0). Continue with ORCID to comment.