6 citations · 12 across the 6 of their papers we have counts for
5 papers · 1 filter
Data-driven Discovery of Lie Symmetries and First Integrals with Latent ODEs
Matt L. Wiemman, Peter Melchior
We present LatentLieODE, a novel neural ODE method to discover linear Lie symmetries and first integrals of the learned dynamics from timeseries observations such as video inputs.…
Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance
Matt L. Wiemann, Peter Melchior, Andrew K. Saydjari
Noise injection is a well-known technique in stochastic optimization. We report its surprising effectiveness with an interleaved (on-off-on-off...) rather than the usual monotonic…
A novel approach to classification of ECG arrhythmia types with latent ODEs
Angelina Yan, Matt L. Sampson, Peter Melchior
12-lead ECGs with high sampling frequency are the clinical gold standard for arrhythmia detection, but their short-term, spot-check nature often misses intermittent events. Wearabl…
Optimization as a Dynamical System: Generative Schedules from Latent ODEs
Matt L. Sampson, Peter Melchior
We present a new meta-learning method to determine the optimal learning rate schedule for gradient descent. It leverages training runs from a hyperparameter search to learn a laten…
Path-minimizing Latent ODEs for improved extrapolation and inference
Matt L. Sampson, Peter Melchior
Latent ODE models provide flexible descriptions of dynamic systems, but they can struggle with extrapolation and predicting complicated non-linear dynamics. The latent ODE approach…