Affiliation:
1. Departments of CSE and ECE UC San Diego La Jolla California USA
2. Halıcıoğlu Data Science Institute UC San Diego La Jolla California USA
3. School of Technology and Engineering National University San Diego California USA
Abstract
AbstractOptimization is a universal quest, reflecting the basic human need to do better. Improved optimizations of energy‐efficiency, safety, robustness, and other criteria in engineered systems would bring incalculable societal benefits. But, fundamental challenges of scale and complexity keep many such real‐world optimization needs beyond reach. This article describes The Institute for Learning‐enabled Optimization at Scale (TILOS), an NSF AI Research Institute for Advances in Optimization that aims to overcome these challenges in three high‐stakes use domains: chip design, communication networks, and contextual robotics. TILOS integrates foundational research, translation, education, and broader impacts toward a new nexus of optimization, AI, and data‐driven learning. We summarize central challenges, early progress, and futures for the institute.
Funder
Directorate for Computer and Information Science and Engineering
Reference16 articles.
1. Bustany I. A. B.Kahng Y.Koutis B.Pramanik andZ.Wang.2022. “SpecPart: A Supervised Spectral Framework for Hypergraph Partitioning Solution Improvement.” InProceedings of the IEEE/ACM International Conference on Computer‐Aided Design.
2. Cheng C.‐K. A. B.Kahng S.Kundu Y.Wang andZ.Wang.2023. “Assessment of Reinforcement Learning for Macro Placement.” InProceedings of theACM/IEEEInternationalSymposium on Physical Design 158–166.
3. CHIPS and Science Act H.R.4346 117th Congress (2021–2022) Public Law No: 117‐167 (08/09/2022).https://www.congress.gov/bill/117th‐congress/house‐bill/4346/text
4. CHIPS for America National Institute of Standards and Technology (NIST) U.S. Department of Commerce.https://www.nist.gov/chips
5. Duruisseaux V. T.Duong M.Leok andN.Atanasov.2023. “Lie Group Forced Variational Integrator Networks for Learning and Control of Robot Systems.”PMLR Learning for Dynamics and Control Conference (L4DC).