Related papers: The Forecast After the Forecast: A Post-Processing…

Post-training improves large language models (LLMs) but often worsens confidence calibration, leading to systematic overconfidence. Recent unsupervised post-hoc methods for post-trained LMs (PoLMs) mitigate this by aligning PoLM confidence…

The recent revolution in data-driven methods for weather forecasting has lead to a fragmented landscape of complex, bespoke architectures and training strategies, obscuring the fundamental drivers of forecast accuracy. Here, we demonstrate…

Rapid expansion of model size has emerged as a key challenge in time series forecasting. From early Transformer with tens of megabytes to recent architectures like TimesNet with thousands of megabytes, performance gains have often come at…

Deepfake (DF) detectors face significant challenges when deployed in real-world environments, particularly when encountering test samples deviated from training data through either postprocessing manipulations or distribution shifts. We…

Reliable forecasts of quasi-stationary, recurrent, and persistent large-scale atmospheric circulation patterns (weather regimes) are crucial for various socio-economic sectors. Despite steady progress, probabilistic weather regime…

Future trajectories play an important role across domains such as autonomous driving, hurricane forecasting, and epidemic modeling, where practitioners commonly generate ensemble paths by sampling probabilistic models or leveraging multiple…

Recent efforts have been dedicated to enhancing time series forecasting accuracy by introducing advanced network architectures and self-supervised pretraining strategies. Nevertheless, existing approaches still exhibit two critical…

Sequence modeling faces challenges in capturing long-range dependencies across diverse tasks. Recent linear and transformer-based forecasters have shown superior performance in time series forecasting. However, they are constrained by their…

Stock trend forecasting is a fundamental task of quantitative investment where precise predictions of price trends are indispensable. As an online service, stock data continuously arrive over time. It is practical and efficient to…

Reliable uncertainty estimates are an important tool for helping autonomous agents or human decision makers understand and leverage predictive models. However, existing approaches to estimating uncertainty largely ignore the possibility of…

A common forecasting setting in real world applications considers a set of possibly heterogeneous time series of the same domain. Due to different properties of each time series such as length, obtaining forecasts for each individual time…

Time series forecasting is a fundamental task emerging from diverse data-driven applications. Many advanced autoregressive methods such as ARIMA were used to develop forecasting models. Recently, deep learning based methods such as DeepAr,…

Multivariate time series forecasting with hierarchical structure is pervasive in real-world applications, demanding not only predicting each level of the hierarchy, but also reconciling all forecasts to ensure coherency, i.e., the forecasts…

Proactive autoscaling for containerized workloads depends on knowing the provisioning delay, i.e., the time between a scaling decision and the moment new capacity is ready to serve traffic. In practice, this cold-start duration can vary…

Modern adaptive optimization methods, such as Adam and its variants, have emerged as the most widely used tools in deep learning over recent years. These algorithms offer automatic mechanisms for dynamically adjusting the update step based…

When training predictive models on data with missing entries, the most widely used and versatile approach is a pipeline technique where we first impute missing entries and then compute predictions. In this paper, we view prediction with…

Deep learning utilizing transformers has recently achieved a lot of success in many vital areas such as natural language processing, computer vision, anomaly detection, and recommendation systems, among many others. Among several merits of…

Generating calibrated and sharp neural network predictive distributions for regression problems is essential for optimal decision-making in many real-world applications. To address the miscalibration issue of neural networks, various…

Conformal Prediction methods have finite-sample distribution-free marginal coverage guarantees. However, they generally do not offer conditional coverage guarantees, which can be important for high-stakes decisions. In this paper, we…

Accurate forecasts are vital for supporting the decisions of modern companies. Forecasters typically select the most appropriate statistical model for each time series. However, statistical models usually presume some data generation…