Related papers: Beyond Accuracy: Ensuring Correct Predictions With…

Language model alignment (or, reinforcement learning) techniques that leverage active exploration -- deliberately encouraging the model to produce diverse, informative responses -- offer the promise of super-human capabilities. However,…

Probabilistic forecasts are essential for various downstream applications such as business development, traffic planning, and electrical grid balancing. Many of these probabilistic forecasts are performed on time series data that contain…

Accurate probabilistic predictions can be characterized by two properties -- calibration and sharpness. However, standard maximum likelihood training yields models that are poorly calibrated and thus inaccurate -- a 90% confidence interval…

The rapid dissemination of misinformation through social media increased the importance of automated fact-checking. Furthermore, studies on what deep neural models pay attention to when making predictions have increased in recent years.…

In this paper, we present results on improving out-of-domain weather prediction and uncertainty estimation as part of the \texttt{Shifts Challenge on Robustness and Uncertainty under Real-World Distributional Shift} challenge. We find that…

Data science has the potential to improve business in a variety of verticals. While the lion's share of data science projects uses a predictive approach, to drive improvements these predictions should become decisions. However, such a…

Methods for reasoning under uncertainty are a key building block of accurate and reliable machine learning systems. Bayesian methods provide a general framework to quantify uncertainty. However, because of model misspecification and the use…

Recommender systems present a customized list of items based upon user or item characteristics with the objective of reducing a large number of possible choices to a smaller ranked set most likely to appeal to the user. A variety of…

A rational approximation by a ratio of polynomial functions is a flexible alternative to polynomial approximation. In particular, rational functions exhibit accurate estimations to nonsmooth and non- Lipschitz functions, where polynomial…

In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations. In this manuscript we focus on predictions expressed as General Value Functions:…

We improve reliable, long-horizon, goal-directed navigation in partially-mapped environments by using non-locally available information to predict the goodness of temporally-extended actions that enter unseen space. Making predictions about…

In this work, we investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reasoning. Our exploration mainly comprises of following three…

Model calibration, which is concerned with how frequently the model predicts correctly, not only plays a vital part in statistical model design, but also has substantial practical applications, such as optimal decision-making in the real…

Time series forecasting is crucial for applications like resource scheduling and risk management, where multi-step predictions provide a comprehensive view of future trends. Uncertainty Quantification (UQ) is a mainstream approach for…

Artificial Intelligence (AI) technologies have profoundly transformed the field of remote sensing, revolutionizing data collection, processing, and analysis. Traditionally reliant on manual interpretation and task-specific models, remote…

The ability to explain decisions made by AI systems is highly sought after, especially in domains where human lives are at stake such as medicine or autonomous vehicles. While it is often possible to approximate the input-output relations…

Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning tasks based on a set of human-understandable concepts.…

Deep learning models are widely used for image analysis. While they offer high performance in terms of accuracy, people are concerned about if these models inappropriately make inferences using irrelevant features that are not encoded from…

Reliable confidence estimation for the predictions is important in many safety-critical applications. However, modern deep neural networks are often overconfident for their incorrect predictions. Recently, many calibration methods have been…

Prediction+optimization is a common real-world paradigm where we have to predict problem parameters before solving the optimization problem. However, the criteria by which the prediction model is trained are often inconsistent with the goal…