Luca Daniel
Professor, Department of Electrical Engineering and Computer Science
Who they work with
Categories
Luca Daniel is a professor in MIT’s Department of Electrical Engineering and Computer Science, and a principal investigator in the Research Laboratory of Electronics. His research interests include development of numerical techniques related to uncertainty quantification, inverse problems, robust optimization, parameterized model order reduction and integral equation solvers. His current applications of interest include evaluating and improving robustness of deep neural networks as well as of magnetic resonance imaging scanners, silicon photonics integrated systems, and electrical power distribution networks.
Daniel has received best-paper awards from several journals of the Institute of Electrical and Electronics Engineers. Other honors include an IBM Corporation Faculty Award, an IEEE Early Career Award in Electronic Design Automation, and the MIT School of Engineering’s Spira Award for Excellence in Teaching. He earned a PhD in electrical engineering and computer sciences at the University of California, Berkeley.
Selected Publications
- Zhang, W.,Nguyen, L. M., Weng, L., Das, S., Megretski, A., Daniel, L. (2023). ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction. International Conference on Machine Learning (ICML).
- Ko, C., Chen, P., Mohapatra, J., Das, P., Daniel, L. (2022). SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data. Conference on Neural Information Processing Systems (NeurIPS).
- Das, S., Daniel, L., Weng, L., Nguyen, L. M., Zhang, W., Megretski, A. (2022). Fast Convergence for Unstable Reinforcement Learning Problems by Logarithmic Mapping. International Conference on Machine Learning (ICML) Workshop on Decision Awareness in Reinforcement Learning.
- Weng, L., Oikarinen, T., Daniel, L., Megretski, A., Zhang, W. (2021). Robust Deep Reinforcement Learning through Adversarial Loss. Conference on Neural Information Processing Systems (NeurIPS).
- September 30, 2019: MIT News, MIT.nano awards inaugural NCSOFT seed grants for gaming technologies.
- March 7, 2019: MIT News, Combining artificial intelligence with their passions.
- February 20, 2019: Techtalks.com, Robust AI: Protecting neural networks against adversarial attacks.
- January 30, 2019: EE Times, AI Tradeoff: Accuracy or Robustness?
- August 13, 2018: Medium, Getting CLEVER(er): Expanding the Scope of a Robustness Metric for Neural Networks.