Do We Really Need Deep Learning Models for Time Series Forecasting?

• URL: http://arxiv.org/abs/2101.02118v1
• Date: Wed, 6 Jan 2021 16:18:04 GMT
• Title: Do We Really Need Deep Learning Models for Time Series Forecasting?
• Authors: Shereen Elsayed, Daniela Thyssens, Ahmed Rashed, Lars Schmidt-Thieme and Hadi Samer Jomaa
• Abstract summary: Time series forecasting is a crucial task in machine learning, as it has a wide range of applications. Deep learning and matrix factorization models have been recently proposed to tackle the same problem with more competitive performance. In this paper, we try to answer whether these highly complex deep learning models are without alternative.
• Score: 4.2698418800007865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series forecasting is a crucial task in machine learning, as it has a wide range of applications including but not limited to forecasting electricity consumption, traffic, and air quality. Traditional forecasting models relied on rolling averages, vector auto-regression and auto-regressive integrated moving averages. On the other hand, deep learning and matrix factorization models have been recently proposed to tackle the same problem with more competitive performance. However, one major drawback of such models is that they tend to be overly complex in comparison to traditional techniques. In this paper, we try to answer whether these highly complex deep learning models are without alternative. We aim to enrich the pool of simple but powerful baselines by revisiting the gradient boosting regression trees for time series forecasting. Specifically, we reconfigure the way time series data is handled by Gradient Tree Boosting models in a windowed fashion that is similar to the deep learning models. For each training window, the target values are concatenated with external features, and then flattened to form one input instance for a multi-output gradient boosting regression tree model. We conducted a comparative study on nine datasets for eight state-of-the-art deep-learning models that were presented at top-level conferences in the last years. The results demonstrated that the proposed approach outperforms all of the state-of-the-art models.

Related papers

• Learning Augmentation Policies from A Model Zoo for Time Series Forecasting [58.66211334969299]
  We introduce AutoTSAug, a learnable data augmentation method based on reinforcement learning. By augmenting the marginal samples with a learnable policy, AutoTSAug substantially improves forecasting performance.
  arXiv  Detail & Related papers  (2024-09-10T07:34:19Z)
• Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines [74.42485647685272]
  We focus on Generative Masked Language Models (GMLMs) We train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model. We adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality.
  arXiv  Detail & Related papers  (2024-07-22T18:00:00Z)
• A Two-Phase Recall-and-Select Framework for Fast Model Selection [13.385915962994806]
  We propose a two-phase (coarse-recall and fine-selection) model selection framework. It aims to enhance the efficiency of selecting a robust model by leveraging the models' training performances on benchmark datasets. It has been demonstrated that the proposed methodology facilitates the selection of a high-performing model at a rate about 3x times faster than conventional baseline methods.
  arXiv  Detail & Related papers  (2024-03-28T14:44:44Z)
• Optimizing Dense Feed-Forward Neural Networks [0.0]
  We propose a novel feed-forward neural network constructing method based on pruning and transfer learning. Our approach can compress the number of parameters by more than 70%. We also evaluate the transfer learning level comparing the refined model and the original one training from scratch a neural network.
  arXiv  Detail & Related papers  (2023-12-16T23:23:16Z)
• Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling [69.60713300418467]
  Learning to jump is a general recipe for generative modeling of various types of data. We demonstrate when learning to jump is expected to perform comparably to learning to denoise, and when it is expected to perform better.
  arXiv  Detail & Related papers  (2023-05-28T05:38:28Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. This creates a barrier to fusing knowledge across individual models to yield a better single model. We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• Revealing Secrets From Pre-trained Models [2.0249686991196123]
  Transfer-learning has been widely adopted in many emerging deep learning algorithms. We show that pre-trained models and fine-tuned models have significantly high similarities in weight values. We propose a new model extraction attack that reveals the model architecture and the pre-trained model used by the black-box victim model.
  arXiv  Detail & Related papers  (2022-07-19T20:19:03Z)
• Model Selection, Adaptation, and Combination for Deep Transfer Learning through Neural Networks in Renewable Energies [5.953831950062808]
  We conduct the first thorough experiment for model selection and adaptation for transfer learning in renewable power forecast. We adopt models based on data from different seasons and limit the amount of training data. We show how combining multiple models through ensembles can significantly improve the model selection and adaptation approach.
  arXiv  Detail & Related papers  (2022-04-28T05:34:50Z)
• Boosted Embeddings for Time Series Forecasting [0.6042845803090501]
  We propose a novel time series forecast model, DeepGB. We formulate and implement a variant of Gradient boosting wherein the weak learners are DNNs whose weights are incrementally found in a greedy manner over iterations. We demonstrate that our model outperforms existing comparable state-of-the-art models using real-world sensor data and public dataset.
  arXiv  Detail & Related papers  (2021-04-10T14:38:11Z)
• Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation [97.42894942391575]
  We propose FAST-DAD to distill arbitrarily complex ensemble predictors into individual models like boosted trees, random forests, and deep networks. Our individual distilled models are over 10x faster and more accurate than ensemble predictors produced by AutoML tools like H2O/AutoSklearn.
  arXiv  Detail & Related papers  (2020-06-25T09:57:47Z)

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.