6 citations · 12 across the 6 of their papers we have counts for
6 papers
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…
Disentangling transients and their host galaxies with Scarlet2: A framework to forward model multi-epoch imaging
Charlotte Ward, Peter Melchior, Matt L. Sampson +6
Many science cases for wide-field time-domain surveys rely on accurate identification and characterization of the galaxies hosting transient and variable objects. In the era of the…
Score-matching neural networks for improved multi-band source separation
Matt L. Sampson, Peter Melchior, Charlotte Ward +1
We present the implementation of a score-matching neural network that represents a data-driven prior for non-parametric galaxy morphologies. The gradients of this prior can be inco…