Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysis

• URL: http://arxiv.org/abs/2511.00989v1
• Date: Sun, 02 Nov 2025 16:03:59 GMT
• Title: Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysis
• Authors: Asal Meskin, Alireza Mirrokni, Ali Najar, Ali Behrouz,
• Abstract summary: We present Hydra, a by-design two-headed meta-in-context memory module.<n>It learns how to memorize patterns at test time by prioritizing time series patterns.<n>We also present a new 2D-chunkwise training algorithm that approximates the actual recurrence with $times 10$ efficiency improvement.
• Score: 9.59658906532313
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, effectively modeling multivariate time series has gained significant popularity, mainly due to its wide range of applications, ranging from healthcare to financial markets and energy management. Transformers, MLPs, and linear models as the de facto backbones of modern time series models have shown promising results in single-variant and/or short-term forecasting. These models, however: (1) are permutation equivariant and so lack temporal inductive bias, being less expressive to capture the temporal dynamics; (2) are naturally designed for univariate setup, missing the inter-dependencies of temporal and variate dimensions; and/or (3) are inefficient for Long-term time series modeling. To overcome training and inference efficiency as well as the lack of temporal inductive bias, recently, linear Recurrent Neural Networks (RNNs) have gained attention as an alternative to Transformer-based models. These models, however, are inherently limited to a single sequence, missing inter-variate dependencies, and can propagate errors due to their additive nature. In this paper, we present Hydra, a by-design two-headed meta in-context memory module that learns how to memorize patterns at test time by prioritizing time series patterns that are more informative about the data. Hydra uses a 2-dimensional recurrence across both time and variate at each step, which is more powerful than mixing methods. Although the 2-dimensional nature of the model makes its training recurrent and non-parallelizable, we present a new 2D-chunk-wise training algorithm that approximates the actual recurrence with $\times 10$ efficiency improvement, while maintaining the effectiveness. Our experimental results on a diverse set of tasks and datasets, including time series forecasting, classification, and anomaly detection show the superior performance of Hydra compared to state-of-the-art baselines.

Related papers

• DiTS: Multimodal Diffusion Transformers Are Time Series Forecasters [50.43534351968113]
  Existing generative time series models do not address the multi-dimensional properties of time series data well.<n>Inspired by Multimodal Diffusion Transformers that integrate textual guidance into video generation, we propose Diffusion Transformers for Time Series (DiTS)
  arXiv  Detail & Related papers  (2026-02-06T10:48:13Z)
• Generative Models for Long Time Series: Approximately Equivariant Recurrent Network Structures for an Adjusted Training Scheme [4.327763441385371]
  We present a simple yet effective generative model for time series data based on a Variational Autoencoder (VAE) with recurrent layers.<n>Our method introduces an adapted training scheme that progressively increases the sequence length.<n>By leveraging the recurrent architecture, the model maintains a constant number of parameters regardless of sequence length.
  arXiv  Detail & Related papers  (2025-05-08T07:52:37Z)
• WaveGNN: Modeling Irregular Multivariate Time Series for Accurate Predictions [3.489870763747715]
  Real-world time series often exhibit irregularities such as misaligned timestamps, missing entries, and variable sampling rates.<n>Existing approaches often rely on imputation, which can introduce biases.<n>We present WaveGNN, a novel framework designed to embed irregularly sampled time series data for accurate predictions.
  arXiv  Detail & Related papers  (2024-12-14T00:03:44Z)
• UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting [98.12558945781693]
  We propose a transformer-based model UniTST containing a unified attention mechanism on the flattened patch tokens. Although our proposed model employs a simple architecture, it offers compelling performance as shown in our experiments on several datasets for time series forecasting.
  arXiv  Detail & Related papers  (2024-06-07T14:39:28Z)
• Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models [5.37935922811333]
  State Space Models (SSMs) are classical approaches for univariate time series modeling. We present Chimera that uses two input-dependent 2-D SSM heads with different discretization processes to learn long-term progression and seasonal patterns. Our experimental evaluation shows the superior performance of Chimera on extensive and diverse benchmarks.
  arXiv  Detail & Related papers  (2024-06-06T17:58:09Z)
• Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values [67.76168547245237]
  We introduce a novel framework called GST-Pro, which utilizes a graphtemporal process and anomaly scorer to detect anomalies. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-11T10:10:16Z)
• Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs [50.25683648762602]
  We introduce Koopman VAE, a new generative framework that is based on a novel design for the model prior. Inspired by Koopman theory, we represent the latent conditional prior dynamics using a linear map. KoVAE outperforms state-of-the-art GAN and VAE methods across several challenging synthetic and real-world time series generation benchmarks.
  arXiv  Detail & Related papers  (2023-10-04T07:14:43Z)
• DuETT: Dual Event Time Transformer for Electronic Health Records [14.520791492631114]
  We introduce the DuETT architecture, an extension of Transformers designed to attend over both time and event type dimensions. DuETT uses an aggregated input where sparse time series are transformed into a regular sequence with fixed length. Our model outperforms state-of-the-art deep learning models on multiple downstream tasks from the MIMIC-IV and PhysioNet-2012 EHR datasets.
  arXiv  Detail & Related papers  (2023-04-25T17:47:48Z)
• TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis [80.56913334060404]
  Time series analysis is of immense importance in applications, such as weather forecasting, anomaly detection, and action recognition. Previous methods attempt to accomplish this directly from the 1D time series. We ravel out the complex temporal variations into the multiple intraperiod- and interperiod-variations.
  arXiv  Detail & Related papers  (2022-10-05T12:19:51Z)
• Multi-scale Attention Flow for Probabilistic Time Series Forecasting [68.20798558048678]
  We propose a novel non-autoregressive deep learning model, called Multi-scale Attention Normalizing Flow(MANF) Our model avoids the influence of cumulative error and does not increase the time complexity. Our model achieves state-of-the-art performance on many popular multivariate datasets.
  arXiv  Detail & Related papers  (2022-05-16T07:53:42Z)
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder [59.69303945834122]
  We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series. Our model parameterizes mean and variance for each time-stamp with flexible neural networks. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
  arXiv  Detail & Related papers  (2021-02-02T06:15:15Z)
• Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows [8.859284959951204]
  Time series forecasting is fundamental to scientific and engineering problems. Deep learning methods are well suited for this problem. We show that it improves over the state-of-the-art for standard metrics on many real-world data sets.
  arXiv  Detail & Related papers  (2020-02-14T16:16:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.