Recently there has been a surge of interest in operations research (OR) and the machine
learning (ML) community in combining prediction algorithms and optimization techniques to …

Artificial intelligence has recently experienced remarkable advances, fueled by large
models, vast datasets, accelerated hardware, and, last but not least, the transformative …

The conjoining of dynamical systems and deep learning has become a topic of great
interest. In particular, neural differential equations (NDEs) demonstrate that neural networks …

Attribution methods are a popular class of explainability methods that use heatmaps to
depict the most important areas of an image that drive a model decision. Nevertheless …

We present Theseus, an efficient application-agnostic open source library for differentiable
nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …

The adjoint method provides an efficient way to compute sensitivities for system models with
a large number of inputs. However, implementing the adjoint method requires significant …

Although disentangled representations are often said to be beneficial for downstream tasks,
current empirical and theoretical understanding is limited. In this work, we provide evidence …

Modern neural models trained on textual data rely on pre-trained representations that
emerge without direct supervision. As these representations are increasingly being used in …

We study the problem of combining neural networks with symbolic reasoning. Recently
introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as …

Attention based models such as Transformers involve pairwise interactions between data
points, modeled with a learnable attention matrix. Importantly, this attention matrix is …