REVIEW 4 cited by
Soft-DTW: a Differentiable Loss Function for Time-Series
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
read the original abstract
We propose in this paper a differentiable learning loss between time series, building upon the celebrated dynamic time warping (DTW) discrepancy. Unlike the Euclidean distance, DTW can compare time series of variable size and is robust to shifts or dilatations across the time dimension. To compute DTW, one typically solves a minimal-cost alignment problem between two time series using dynamic programming. Our work takes advantage of a smoothed formulation of DTW, called soft-DTW, that computes the soft-minimum of all alignment costs. We show in this paper that soft-DTW is a differentiable loss function, and that both its value and gradient can be computed with quadratic time/space complexity (DTW has quadratic time but linear space complexity). We show that this regularization is particularly well suited to average and cluster time series under the DTW geometry, a task for which our proposal significantly outperforms existing baselines. Next, we propose to tune the parameters of a machine that outputs time series by minimizing its fit with ground-truth labels in a soft-DTW sense.
Forward citations
Cited by 4 Pith papers
-
Generative Augmentation for EEG Motor Imagery Classification: A Class-Conditional VAE with Cycle-Consistent Decoder Refinement
Synthetic EEG from a class-conditional VAE with covariance and cycle-consistency losses captures class structure but provides no statistically reliable accuracy gain for four downstream classifiers.
-
Formally Verified Neurosymbolic Trajectory Learning via Tensor-based Linear Temporal Logic on Finite Traces
A formally verified Isabelle/HOL specification of tensor-based LTLf semantics yields a verified differentiable loss and derivative, automatically extracted to OCaml and used to train trajectory-planning networks in PyTorch.
-
Benchmarking Unsupervised Strategies for Anomaly Detection in Multivariate Time Series
Across ten public datasets, a reconstruction-based inverted transformer with per-variate anomaly labelling achieves the best or tied best MCC on most datasets, but the comparison is weakened by test-set-based configur...
-
Diffeomorphic Temporal Alignment Nets for Time-series Joint Alignment and Averaging
A deep learning framework with a new inverse-consistency loss aligns and averages time series across 128 UCR datasets without per-dataset regularization tuning.
Discussion (0). Continue with ORCID to comment.