I am an Assistant Professor in the Computer Science Department with the School of Computer Science at Carnegie Mellon University. In addition to my full-time role at CMU, I also serve as Chief Scientist of AI Research for the Bosch Center for AI (BCAI), working in the Pittsburgh Office. BCAI also generously provides funding for much of the research in my group.
My group’s work focuses on machine learning, optimization, and control. Specifically, much of our work aims at making deep learning algorithms safer, more robust, and more explainable; to these ends, we have worked on methods for training provably robust deep learning systems, and including more complex “modules” (such as optimization solvers) within the loop of deep architectures. We also focus on several application domains, with a particular focus on applications in smart energy and sustainability domains.
- 7/18: Eric Wong to present Provable defenses against adversarial examples via the convex outer adversarial polytope at ICML 2018.
- 6/18: Zico Kolter presents lectures on Reinforcement Learning at the ICAPS 2018 Summer School.
- 12/17: Vaishnavh Nagarajan presents Gradient descent GAN optimization is locally stable as a oral presentation at NIPS 2017.
- 12/17: Priya Donti presents Task-based End-to-end Model Learning in Stochastic Optimization as a poster at NIPS 2017.
- 8/17: Brandon Amos presents Input Convex Neural Networks and OptNet: Differentiable Optimization as a Layer in Neural Networks at ICML.
- 8/17: Alnur Ali and Eric Wong present A Semismooth Newton Method for Fast, Generic Convex Programming at ICML.
- 4/17: Zico Kolter receives DARPA Young Faculty Award in 2017 class.
- 2/17: Po-wei Wang presents Polynomial optimization methods for matrix factorization at AAAI 2017.
12/16: Alnur Ali presents The Multiple Quantile Graphical Model at NIPS 2016 main conference.
- 12/16: Brandon Amos presents work on input convex neural networks for reinforcement learning at NIPS 2016 workshop on deep reinforcement learning.
- 12/16: Po-wei Wang presents work on the mixing method for fast MAXCUT-SDP solutions at NIPS 2016 workshop on Learning in high dimensions with structure.
- 11/16: Received DARPA SAGA seed project to investigate fast methods for stochastic programming.
- 9/16: Our preprint Input Convex Neural Networks is available on Arxiv.
- 8/16: Received DARPA RADICS award (with NRECA) to develop machine learning approaches to cybersecurity in electrical grid networks.
- 7/16: Xiao Zhang presents Model Predictive Control of Industrial Loads and Energy Storage for Demand Response, recipient of best paper award, at PES General meeting.
- The beginning of time (or this redesigned website, rather).