Bounded Rationality & Metareasoning: Selected papers


Bounded optimality & anytime algorithms

 E. Horvitz, Reasoning about Beliefs and Actions under Computational Resource Constraints, UAI 1987, pp. 429-444. (Extended book version.)



Principles of metareasoning

E.J. Horvitz, G.F. Cooper, D.E. Heckerman, Reflection and action under scarce resources: Theoretical principles and empirical study. IJCAI 1989, pp. 1121-1127.


C.H. Lin, A. Kolobov, E. Kamar, E. Horvitz. Metareasoning for Planning Under Uncertainty. In Proceedings of IJCAI 2015.



Cost of thinking

E.J. Horvitz, Reasoning under varying and uncertain resource constraints. AAAI 1988, pp. 111-116.



Principles of streaming intelligence

 E. Horvitz. Principles and Applications of Continual ComputationAI Journal, 126:159-196 (2001).


 D. Shahaf and E. Horvitz. Investigations of Continual Computation, IJCAI 2009.



From reasoning to reflex

 D. Heckerman, J.S. Breese, E. Horvitz, The Compilation of Decision Models, UAI 1989, pp. 162-173.


S. Rosenthal, D. Bohus, E. Kamar, E. Horvitz. Look versus Leap: Computing Value of Information with High-Dimensional Streaming Evidence, IJCAI 2013.



Computational rationality as convergent paradigm

 S.J. Gershman, E.J. Horvitz, J.B. Tenenbaum. Computational Rationality: A Converging Paradigm for Intelligence in Brains, Minds, and Machines, 16 July 2015, Science 349. 273-278.



Predicting run time & learning policies to solve hard computing problems


E. Horvitz, Y. Ruan, C. Gomes, H. Kautz, B. Selman, D. M. Chickering. A Bayesian Approach to Tackling Hard Computational Problems. UAI 2001, pp. 235-244.


H. Kautz, E. Horvitz, Y. Ruan, C. Gomes, B. Selman. Dynamic Restart Policies. AAAI 2002.



Inference under bounded resources


E.J. Horvitz, H.J. Suermondt, G.F. Cooper. Bounded conditioning: Flexible inference for decisions under scarce resources. UAI 1989, pp. 182-193.


E. Horvitz and A. Klein. Studies of Theorem Proving under Limited Resources. UAI 1995.


P. Dagum and E. Horvitz. A Bayesian Analysis of Simulation Algorithms for Inference in Belief Networks. Networks, 23:499-516, 1993.



Ideal partition of resources to reasoning vs metareasoning


E.J. Horvitz and J.S. Breese, Ideal Partition of Resources for Metareasoning. Stanford University CS Department Technical Report KSL-90-26, 1990.


J.S. Breese and E.J. Horvitz. Ideal Reformulation of Belief Networks , UAI 1990, pp. 64-72.



Metareasoning via reinforcement learning


A. Modi, D. Dey, A. Agarwal, A. Swaminathan, B. Nushi, S. Andrist, E. Horvitz. Metareasoning in Modular Software Systems: On-the-Fly Configuration using Reinforcement Learning with Rich Contextual Representations, AAAI 2020.



Computing value of information under bounded resources


E. Kamar and E. Horvitz. Light at the End of the Tunnel: A Monte Carlo Approach to Computing Value of Information, AAMAS 2013, St. Paul, Minnesota, May 2013.


D. Heckerman, E. Horvitz, and B. Middleton, An approximate nonmyopic computation for value of information, IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 15 (1993), 3:292-298.



Teaching neural models when to ask people for help

 B. Wilder, E. Horvitz, E. Kamar. Learning to Complement Humans, IJCAI 2020.



Blindspots in learning and reasoning


H. Lakkaraju, E. Kamar, R. Caruana, E. Horvitz. Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration, AAAI 2017. 


B. Nushi, E. Kamar, E. Horvitz, D. Kossmann. On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems, AAAI 2017. 


R. Ramakrishnan, E. Kamar, B. Nushi, D. Dey, J. Shah, E. Horvitz. Overcoming Blind Spots in the Real World: Leveraging Complementary Abilities for Joint Execution, AAAI 2019.



Reflection about decision models & their completeness


K.L. Poh and E. Horvitz. Reasoning about the Value of Decision Model Refinement: Methods and Application. UAI 1993, Washington DC, July 1993, pp. 174-182.


D. Heckerman and E. Horvitz. Problem Formulation as the Reduction of a Decision Problem. Proceedings of the Conference on Uncertainty in Artificial Intelligence, Cambridge, MA July 1990, pp. 82-89.



Utility-theoretic approach to abstraction


E. Horvitz and A. Klein, Utility-Based Abstraction and Categorization. UAI 1993, pp. 128-135.



Principles to Applications


E. Horvitz and G. Rutledge. Time-Dependent Utility and Action under Uncertainty. UAI 1991, pp. 151-158. Morgan Kaufman, 1991.


E. Horvitz and A. Seiver. Time-Critical Action: Representations and Application. UAI 1997.


A. Kapoor, S. Baker, S. Basu, E. Horvitz. Memory Constrained Face Recognition, CVPR 2012.


A. Kolobov, Y. Peres, C. Lu, E. Horvitz. Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling, NeurIPS 2019.


A. Kapoor and E. Horvitz. On Discarding, Caching, and Recalling Samples in Active Learning, UAI 2007.


A. Kapoor and E. Horvitz. Principles of Lifelong Learning for Predictive User Modeling. User Modeling 2007, Corfu, Greece.


E. Horvitz. Computation and Action under Bounded Resources. PhD Dissertation, Stanford University, 1990 (pdf).



Canadian Traveler Problem


D. Dey, A. Kolobov, R. Caruana, E. Kamar, E. Horvitz, A. Kapoor. Gauss Meets Canadian Traveler: Shortest-Path Problems with Correlated Natural Dynamics, AAMAS 2014, Paris, France, May 2014.





E. Horvitz. Artificial Intelligence in the Open World, AAAI Presidential Lecture, Chicago, IL, Association for the Advancement of AI, July 2008.


E. Horvitz and S. Zilberstein, Computational Tradeoffs Under Bounded Resources, Artificial Intelligence Journal, 126:1-4, Elsevier Science, February 2001.


E.J. Horvitz, Rational Metareasoning and Compilation for Optimizing Decisions Under Bounded Resources. Proceedings of Computational Intelligence, Milan, Italy, September 1989. Association for Computing Machinery.


E. Horvitz, Some Fundamental Problems and Opportunities from the Standpoint of Rational Agency. Stanford University Computer Science Department Technical Report KSL-89-30, 1989.


E. Horvitz. Research on Principles of Bounded Rationality. AAAI Spring Symposium on Artificial Intelligence in Medicine, Stanford CA, March 1990.


B. Selman, R. Brooks, T. Dean, E. Horvitz, T. Mitchell, N. Nilsson. Challenge Problems for Artificial Intelligence. AAAI 1996. pp. 1340-1345.



Human dimension on bounded rationality


E. Horvitz, S. Dumais, P. Koch. Learning Predictive Models of Memory Landmarks, CogSci 2004.


M. Ringel, E. Cutrell, S. Dumais, E. Horvitz. Milestones in Time: The Value of Landmarks in Retrieving Information from Personal Stores. CHI 2003.


E. Horvitz and J. Apacible. Learning and Reasoning about Interruption. ICMI 2003.


E. Horvitz, C. M. Kadie, T. Paek, D. Hovel. Models of Attention in Computing and Communications: From Principles to Applications, CACM 46(3):52-59, March 2003.


E. Horvitz, A. Jacobs, D. Hovel. Attention-Sensitive Alerting, UAI 99, pp. 305-313.


S.T. Iqbal, Y.C. Ju, E. Horvitz. Cars, Calls, and Cognition: Investigating Driving and Divided Attention, CHI 2010.


E. Horvitz and M Barry. Display of Information for Time-Critical Decision Making. UAI 1995.


E. Horvitz and J. Lengyel. Perception, Attention, and Resources: A Decision-Theoretic Approach to Graphics Rendering. UAI 1997, pp. 238-249.


E. Horvitz. Principles of Mixed-Initiative User Interfaces. CHI 1999.


A. Kapoor, B. Lee, D. Tan, E. Horvitz. Learning to Learn: Algorithmic Inspirations from Human Problem Solving, AAAI 2012.


A. Kapoor, D. Tan, P. Shenoy, E. Horvitz. Complementary Computing for Visual Tasks: Meshing Computer Vision with Human Visual Processing, IEEE International Conference on Automatic Face and Gesture Recognition.


E. Horvitz, J. Apacible, and P. Koch. BusyBody: Creating and Fielding Personalized Models of the Cost of Interruption, CSCW 2004.


E. Horvitz, D. Heckerman, K. Ng, B. Nathwani, Heuristic Abstraction in the Decision-Theoretic Pathfinder System, Symposium on Computer Applications in Medical Care, Washington DC, IEEE Press: Silver Springs, MD, November 1989.


E. Horvitz, J. Apacible, M. Subramani. Balancing Awareness and Interruption: Investigation of Notification Deferral Policies. User Modeling 2005. 


S.T. Iqbal and E. Horvitz. Notifications and Awareness: A Field Study of Alert Usage and Preferences, CSCW 2010.


S. Iqbal and E. Horvitz. Conversations Amidst Computing: A Study of Interruptions and Recovery of Task Activity. User Modeling 2005.


M. Czerwinski, M., E. Horvitz, and S. Wilhite. A Diary Study of Task Switching and Interruptions, CHI 2004.


Czerwinski, M. and Horvitz, E. An Investigation of Memory for Daily Computing Events. HCI 2002.


E. Cutrell, M. Czerwinski, and E. Horvitz. Notification, Disruption and Memory: Effects of Messaging Interruptions on Memory and Performance. Interact 2001.


M. Czerwinski, E. Cutrell, and E. Horvitz. Instant Messaging and Interruption: Influence of Task Type on Performance, OZCHI 2000.


M. Czerwinski, E. Cutrell, and E. Horvitz. Instant Messaging: Effects of Relevance and Time, HCI 2000, p. 71-76.


E. Cutrell, M. Czerwinski, and E. Horvitz. Effects of Instant Messaging Interruptions on Computing Tasks. CHI 2000.