Koopa: Learning non-stationary time series dynamics with koopman predictors
Real-world time series are characterized by intrinsic non-stationarity that poses a principal
challenge for deep forecasting models. While previous models suffer from complicated …
challenge for deep forecasting models. While previous models suffer from complicated …
Temporally disentangled representation learning under unknown nonstationarity
In unsupervised causal representation learning for sequential data with time-delayed latent
causal influences, strong identifiability results for the disentanglement of causally-related …
causal influences, strong identifiability results for the disentanglement of causally-related …
Orthogonality-enforced latent space in autoencoders: An approach to learning disentangled representations
J Cha, J Thiyagalingam - International Conference on …, 2023 - proceedings.mlr.press
Noting the importance of factorizing (or disentangling) the latent space, we propose a novel,
non-probabilistic disentangling framework for autoencoders, based on the principles of …
non-probabilistic disentangling framework for autoencoders, based on the principles of …
Sample and predict your latent: modality-free sequential disentanglement via contrastive estimation
Unsupervised disentanglement is a long-standing challenge in representation learning.
Recently, self-supervised techniques achieved impressive results in the sequential setting …
Recently, self-supervised techniques achieved impressive results in the sequential setting …
Generative modeling of regular and irregular time series data via koopman VAEs
Generating realistic time series data is important for many engineering and scientific
applications. Existing work tackles this problem using generative adversarial networks …
applications. Existing work tackles this problem using generative adversarial networks …
Localized Linear Temporal Dynamics for Self-supervised Skeleton Action Recognition
Self-supervised skeleton action recognition has gained notable attention for its reduced
reliance on annotated data. Contrastive learning methods, in particular, have emerged as …
reliance on annotated data. Contrastive learning methods, in particular, have emerged as …
Koopman invertible autoencoder: Leveraging forward and backward dynamics for temporal modeling
Accurate long-term predictions are the foundations for many machine learning applications
and decision-making processes. However, building accurate long-term prediction models …
and decision-making processes. However, building accurate long-term prediction models …
Phase autoencoder for limit-cycle oscillators
We present a phase autoencoder that encodes the asymptotic phase of a limit-cycle
oscillator, a fundamental quantity characterizing its synchronization dynamics. This …
oscillator, a fundamental quantity characterizing its synchronization dynamics. This …
CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process
Identifying the underlying time-delayed latent causal processes in sequential data is vital for
grasping temporal dynamics and making downstream reasoning. While some recent …
grasping temporal dynamics and making downstream reasoning. While some recent …
First-Order Manifold Data Augmentation for Regression Learning
I Kaufman, O Azencot - arXiv preprint arXiv:2406.10914, 2024 - arxiv.org
Data augmentation (DA) methods tailored to specific domains generate synthetic samples
by applying transformations that are appropriate for the characteristics of the underlying data …
by applying transformations that are appropriate for the characteristics of the underlying data …