48 citations · 120 across the 24 of their papers we have counts for
28 papers
A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
Gal Fadlon, Idan Arbiv, Nimrod Berman +1
Generating realistic time series data is critical for applications in healthcare, finance, and science. However, irregular sampling and missing values present significant challenge…
DiffSDA: Unsupervised Diffusion Sequential Disentanglement Across Modalities
Hedi Zisling, Ilan Naiman, Nimrod Berman +2
Unsupervised representation learning, particularly sequential disentanglement, aims to separate static and dynamic factors of variation in data without relying on labels. This rema…
Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
Liran Nochumsohn, Raz Marshanski, Hedi Zisling +1
Time series forecasting (TSF) is critical in domains like energy, finance, healthcare, and logistics, requiring models that generalize across diverse datasets. Large pre-trained mo…
Curvature Enhanced Data Augmentation for Regression
Ilya Kaufman Sirot, Omri Azencot
Deep learning models with a large number of parameters, often referred to as over-parameterized models, have achieved exceptional performance across various tasks. Despite concerns…
Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach
Tal Gonen, Itai Pemper, Ilan Naiman +2
Generative modeling of time series is a central challenge in time series analysis, particularly under data-scarce conditions. Despite recent advances in generative modeling, a comp…
FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical Systems
N. Benjamin Erichson, Vinicius Mikuni, Dongwei Lyu +4
We introduce FLEX (FLow EXpert), a backbone architecture for generative modeling of spatio-temporal physical systems using diffusion models. FLEX operates in the residual space rat…
One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling
Nimrod Berman, Ilan Naiman, Moshe Eliasof +2
Diffusion-based generative models have demonstrated exceptional performance, yet their iterative sampling procedures remain computationally expensive. A prominent strategy to mitig…
A Multi-Task Learning Approach to Linear Multivariate Forecasting
Liran Nochumsohn, Hedi Zisling, Omri Azencot
Accurate forecasting of multivariate time series data is important in many engineering and scientific applications. Recent state-of-the-art works ignore the inter-relations between…
Beyond Data Scarcity: A Frequency-Driven Framework for Zero-Shot Forecasting
Liran Nochumsohn, Michal Moshkovitz, Orly Avner +2
Time series forecasting is critical in numerous real-world applications, requiring accurate predictions of future values based on observed patterns. While traditional forecasting t…
Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
Ilan Naiman, Nimrod Berman, Itai Pemper +3
Lately, there has been a surge in interest surrounding generative modeling of time series data. Most existing approaches are designed either to process short sequences or to handle…
Analyzing Deep Transformer Models for Time Series Forecasting via Manifold Learning
Ilya Kaufman, Omri Azencot
Transformer models have consistently achieved remarkable results in various domains such as natural language processing and computer vision. However, despite ongoing research effor…
Learning Physics for Unveiling Hidden Earthquake Ground Motions via Conditional Generative Modeling
Pu Ren, Rie Nakata, Maxime Lacour +9
Predicting high-fidelity ground motions for future earthquakes is crucial for seismic hazard assessment and infrastructure resilience. Conventional empirical simulations suffer fro…
Sequential Disentanglement by Extracting Static Information From A Single Sequence Element
Nimrod Berman, Ilan Naiman, Idan Arbiv +2
One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequenc…
First-Order Manifold Data Augmentation for Regression Learning
Ilya Kaufman, Omri Azencot
Data augmentation (DA) methods tailored to specific domains generate synthetic samples by applying transformations that are appropriate for the characteristics of the underlying da…
Data Augmentation Policy Search for Long-Term Forecasting
Liran Nochumsohn, Omri Azencot
Data augmentation serves as a popular regularization technique to combat overfitting challenges in neural networks. While automatic augmentation has demonstrated success in image c…
Reviving Life on the Edge: Joint Score-Based Graph Generation of Rich Edge Attributes
Nimrod Berman, Eitan Kosman, Dotan Di Castro +1
Graph generation is integral to various engineering and scientific disciplines. Nevertheless, existing methodologies tend to overlook the generation of edge attributes. However, we…
Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
Ilan Naiman, N. Benjamin Erichson, Pu Ren +2
Generating realistic time series data is important for many engineering and scientific applications. Existing work tackles this problem using generative adversarial networks (GANs)…
Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation
Ilan Naiman, Nimrod Berman, Omri Azencot
Unsupervised disentanglement is a long-standing challenge in representation learning. Recently, self-supervised techniques achieved impressive results in the sequential setting, wh…
Data Representations' Study of Latent Image Manifolds
Ilya Kaufman, Omri Azencot
Deep neural networks have been demonstrated to achieve phenomenal success in many domains, and yet their inner mechanisms are not well understood. In this paper, we investigate the…
Multifactor Sequential Disentanglement via Structured Koopman Autoencoders
Nimrod Berman, Ilan Naiman, Omri Azencot
Disentangling complex data to its latent factors of variation is a fundamental task in representation learning. Existing work on sequential disentanglement mostly provides two fact…
Eigenvalue initialisation and regularisation for Koopman autoencoders
Jack W. Miller, Charles O'Neill, Navid C. Constantinou +1
Regularising the parameter matrices of neural networks is ubiquitous in training deep models. Typical regularisation approaches suggest initialising weights using small random valu…
A Differential Geometry Perspective on Orthogonal Recurrent Models
Omri Azencot, N. Benjamin Erichson, Mirela Ben-Chen +1
Recently, orthogonal recurrent neural networks (RNNs) have emerged as state-of-the-art models for learning long-term dependencies. This class of models mitigates the exploding and…
An Operator Theoretic Approach for Analyzing Sequence Neural Networks
Ilan Naiman, Omri Azencot
Analyzing the inner mechanisms of deep neural networks is a fundamental task in machine learning. Existing work provides limited analysis or it depends on local theories, such as f…
Modes of Homogeneous Gradient Flows
Ido Cohen, Omri Azencot, Pavel Lifshitz +1
Finding latent structures in data is drawing increasing attention in diverse fields such as image and signal processing, fluid dynamics, and machine learning. In this work we exami…