Related papers: Test-Time Efficient Pretrained Model Portfolios fo…
The current landscape in time-series forecasting is dominated by Transformer-based models. Their high parameter count and corresponding demand in computational resources pose a challenge to real-world deployment, especially for commercial…
Pre-trained Large Language Models (LLMs) encapsulate large amounts of knowledge and take enormous amounts of compute to train. We make use of this resource, together with the observation that LLMs are able to transfer knowledge and…
Amounts of historical data collected increase and business intelligence applicability with automatic forecasting of time series are in high demand. While no single time series modeling method is universal to all types of dynamics,…
This paper proposes a framework for developing forecasting models by streamlining the connections between core components of the developmental process. The proposed framework enables swift and robust integration of new datasets,…
Machine learning models have made significant progress in load forecasting, but their forecast accuracy is limited in cases where historical load data is scarce. Inspired by the outstanding performance of large language models (LLMs) in…
We study prediction of future outcomes with supervised models that use privileged information during learning. The privileged information comprises samples of time series observed between the baseline time of prediction and the future…
Motivated by the recent success of time-series foundation models for zero-shot forecasting, we present a methodology for $\textit{in-context fine-tuning}$ of a time-series foundation model. In particular, we design a pretrained foundation…
Time series forecasting drives operational decisions in areas like finance, transportation, and energy. While supervised learning approaches achieve strong performance, they require domain-specific training, feature engineering, and ongoing…
This work studies the problem of time series analysis with generalist (or foundation) models, which are models trained across many data domains. Drawing inspiration from the widespread success of large language models, we consider the…
Deep learning for time series forecasting has seen significant advancements over the past decades. However, despite the success of large-scale pre-training in language and vision domains, pre-trained time series models remain limited in…
We investigate the effectiveness of ensembles of pretrained transformer-based language models on short answer questions using the Kaggle Automated Short Answer Scoring dataset. We fine-tune a collection of popular small, base, and large…
Foundation models have recently gained attention within the field of machine learning thanks to its efficiency in broad data processing. While researchers had attempted to extend this success to time series models, the main challenge is…
Evaluating models on large benchmarks is very resource-intensive, especially during the period of rapid model evolution. Existing efficient evaluation methods estimate the performance of target models by testing them only on a small and…
Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are crucial to meet memory and inference time requirements, as…
We consider small-data, large-scale decision problems in which a firm must make many operational decisions simultaneously (e.g., across a large product portfolio) while observing only a few, potentially noisy, data points per instance.…
While machine learning has witnessed significant advancements, the emphasis has largely been on data acquisition and model creation. However, achieving a comprehensive assessment of machine learning solutions in real-world settings…
Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and…
Decision-making is a dynamic process requiring perception, memory, and reasoning to make choices and find optimal policies. Traditional approaches to decision-making suffer from sample efficiency and generalization, while large-scale…
In recent years, deep learning techniques have outperformed traditional models in many machine learning tasks. Deep neural networks have successfully been applied to address time series forecasting problems, which is a very important topic…
Larger language models have higher accuracy on average, but are they better on every single instance (datapoint)? Some work suggests larger models have higher out-of-distribution robustness, while other work suggests they have lower…