131 citations
- University of California San DiegoUS2 papers
- University of Maryland, College ParkUS2 papers
- Contextual Change (United States)US1 paper
- Decision Systems (United States)US1 paper
- Duke UniversityUS1 paper
- Fudan UniversityCN1 paper
- Massachusetts Institute of TechnologyUS1 paper
- Pennsylvania State UniversityUS1 paper
- San Diego State UniversityUS1 paper
- University of MaineUS1 paper
15 papers
Towards Explaining Deep Neural Network Compression Through a Probabilistic Latent Space
Mahsa Mozafari-Nia, Salimeh Yasaei Sekeh
Despite the impressive performance of deep neural networks (DNNs), their computational complexity and storage space consumption have led to the concept of network compression. Whil…
Safe Control Synthesis with Uncertain Dynamics and Constraints
Kehan Long, Vikas Dhiman, Melvin Leok +2
This paper considers safe control synthesis for dynamical systems with either probabilistic or worst-case uncertainty in both the dynamics model and the safety constraints. We form…
Tunneling dynamics in cosmological bounce models
Martin Bojowald, Brenda Jones
Quasiclassical methods are used to define dynamical tunneling times in models of quantum cosmological bounces. These methods provide relevant new information compared with the trad…
IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography
Alina Jade Barnett, Fides Regina Schwartz, Chaofan Tao +4
Interpretability in machine learning models is important in high-stakes decisions, such as whether to order a biopsy based on a mammographic exam. Mammography poses important chall…
Control Barriers in Bayesian Learning of System Dynamics
Vikas Dhiman, Mohammad Javad Khojasteh, Massimo Franceschetti +1
This paper focuses on learning a model of system dynamics online while satisfying safety constraints. Our objective is to avoid offline system identification or hand-specified mode…
Asset Allocation via Machine Learning and Applications to Equity Portfolio Management
Qing Yang, Zhenning Hong, Ruyan Tian +2
In this paper, we document a novel machine learning based bottom-up approach for static and dynamic portfolio optimization on, potentially, a large number of assets. The methodolog…