Related papers: Ordinal Encoding as a Regularizer in Binary Loss f…
Function-level binary code similarity detection is a crucial aspect of cybersecurity. It enables the detection of bugs and patent infringements in released software and plays a pivotal role in preventing supply chain attacks. A practical…
Prediction of solar flares is an important task in solar physics. The occurrence of solar flares is highly dependent on the structure and the topology of solar magnetic fields. A new method for predicting large (M and X class) flares is…
Classical neural ordinary differential equations (ODEs) are powerful tools for approximating the log-density functions in high-dimensional spaces along trajectories, where neural networks parameterize the velocity fields. This paper…
We analyze and contrast two ways to train machine learning models for solving AC optimal power flow (OPF) problems, distinguished with the loss functions used. The first trains a mapping from the loads to the optimal dispatch decisions,…
We propose a regularisation strategy of classical machine learning algorithms rooted in causality that ensures robustness against distribution shifts. Building upon the anchor regression framework, we demonstrate how incorporating a…
The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach…
Classification of ordinal data is one of the most important tasks of relation learning. In this thesis a novel framework for ordered classes is proposed. The technique reduces the problem of classifying ordered classes to the standard…
The minimization of specific cases in binary classification, such as false negatives or false positives, grows increasingly important as humans begin to implement more machine learning into current products. While there are a few methods to…
Probabilistic-driven classification techniques extend the role of traditional approaches that output labels (usually integer numbers) only. Such techniques are more fruitful when dealing with problems where one is not interested in…
In hierarchical multi-label classification, a persistent challenge is enabling model predictions to reach deeper levels of the hierarchy for more detailed or fine-grained classifications. This difficulty partly arises from the natural…
The explicit regularization and optimality of deep neural networks estimators from independent data have made considerable progress recently. The study of such properties on dependent data is still a challenge. In this paper, we carry out…
Our aim is to calculate the evolution of Algol binaries within the framework of the osculating orbital theory, which considers the perturbing forces acting on the orbit of each star arising from mass exchange via Roche lobe overflow (RLOF).…
We consider the problem of sequential decision making under uncertainty in which the loss caused by a decision depends on the following binary observation. In competitive on-line learning, the goal is to design decision algorithms that are…
In order to understand the flare trigger mechanism, we conducted three-dimensional magnetohydrodynamic simulations using a coronal magnetic field model derived from data observed by the Hinode satellite. Several types of magnetic bipoles…
We initiate the study of fairness for ordinal regression. We adapt two fairness notions previously considered in fair ranking and propose a strategy for training a predictor that is approximately fair according to either notion. Our…
Offline meta-reinforcement learning (OMRL) combines the strengths of learning from diverse datasets in offline RL with the adaptability to new tasks of meta-RL, promising safe and efficient knowledge acquisition by RL agents. However, OMRL…
High-magnification microlensing events provide an important channel to detect planets. Perturbations near the peak of a high-magnification event can be produced either by a planet or a binary companion. It is known that central…
Regularized models are often sensitive to the scales of the features in the data and it has therefore become standard practice to normalize (center and scale) the features before fitting the model. But there are many different ways to…
Probabilistic forecasts are typically obtained using state-of-the-art statistical and machine learning models, with model parameters estimated by optimizing a proper scoring rule over a set of training data. If the model class is not…
Labeling a classification dataset implies to define classes and associated coarse labels, that may approximate a smoother and more complicated ground truth. For example, natural images may contain multiple objects, only one of which is…