Brief Research Statement
My research area is Artificial Intelligence with a focus on large-scale constraint reasoning, optimization, and machine learning. I exploit connections between different research areas — in particular artificial intelligence, operations research, and the theory of algorithms. Central themes of my research are: (1) the synthesis of formal and experimental research for understanding and exploiting problem structure, (2) the integration of concepts from constraint reasoning, convex programming, and machine learning, (3) the integration of (deep) data-intensive learning with inference, reasoning, and optimization and (4) the use of randomization techniques to scale up the performance of complete (exact) search methods. I combine formal analysis with the study of applications in e.g., combinatorial design, multi-agent systems, and scientific discovery. Recently, I have become deeply immersed in the establishment of new field of Computational Sustainability.
Computational Sustainability is a new interdisciplinary research field, with the overarching goal of studying and providing solutions to computational problems for balancing environmental, economic, and societal needs for a sustainable future. Such problems are unique in scale, impact, complexity, and richness, often involving combinatorial decisions, in highly dynamic and uncertain environments, offering challenges but also opportunities for the advancement of the state-of-the-art of computer and information science. Work in Computational Sustainability integrates in a unique way various areas within computer science and applied mathematics, such as constraint reasoning, optimization, machine learning, and dynamical systems. The research necessarily entails a cross-fertilization of approaches and ideas from several research communities, bringing together computer scientists, biologists and environmental scientists, biological and environmental engineers, sociologists, and economists. Concrete examples of computational sustainability challenges range from planning and optimization for wildlife preservation and biodiversity conservation, to poverty mapping, to combining (deep) data-intensive learning with inference, reasoning, and optimization to accelerate the discovery of new renewable materials such as solar fuels.
In 2008, under the NSF Expeditions in Computing program, we created the Institute for Computational Sustainability (ICS) to forge a highly interdisciplinary effort to nurture the field of Computational Sustainability. In 2015, we received another NSF expedition to further expand Computational Sustainability and create a large scale Computational Sustainability network, CompSustNet. Our vision is that computer science can — and should — play a key role in increasing the efficiency and effectiveness of the way we manage and allocate our natural resources. The plethora of challenging computational research questions posed by sustainability problems, pushing the boundaries of current computational methods, also provides an exciting way to broaden and advance the state-of-the-art of computer science.
I am also interested in scientific discovery. UDiscoverIt seeks to accelerate scientific discovery by leveraging human intuition within processes of data analysis, inference, and data collection. We are integrating human computation, crowdsourcing, and citizen science into (deep) data-intensive learning, inference, reasoning, and optimization algorithms.
Cornell Graduate Research Field Memberships
I'm a member of the following Cornell graduate research fields:
- Computer Science
- Information Science
- Applied Mathematics
- Applied Economics and Management
- City and Regional Planning
- Johan Bjorck (Computer Science)
- Yexiang Xue (Computer Science)
- Qinru Shi (Applied Mathematics)
- Bistra Dilkina (Computer Science; now assistant professor at Georgia Tech.)
- Stefano Ermon (Computer Science;now assistant professor at Stanford University)
- Ronan Le Bras (Computer Science; now researcher at Paul Allen Inst. for AI )
- Yunsong Guo (Computer Science; now at Pinterest)
Current and Former Postdocs
- Xiaojian Wu
- Theo Damoulas (2009-2013, now assistant professor at the University of Warwick, UK)
- Carlos Ansotegui (2005, now Professor at Lleida University, Spain)
- Ramon Bejar (2003, now Professor at Lleida University, Spain)
- Carmel Domshlak (2003, now Professor at Technion University, Israel)
- Cesar Fernandez (2004, now Professor at Lleida University, Spain)
- Willem van Hoeve (2006-2008, now Associate Professor at CMU)
- Ashish Sabharwal (2005-2010, now at Paul Allen Inst. for AI)
- Meinolf Sellmann (2004, now at IBM T.J. Watson Research Center)
607-255-9189 (voice); 607-255-4428 (fax)
gomes at cs.cornell.edu