Papers by Solomon Shimony
Uncertainty in Artificial Intelligence, 1997
ABSTRACT Wide-angle sonar mapping of the environment by mobile robot is nontrivial due to several... more ABSTRACT Wide-angle sonar mapping of the environment by mobile robot is nontrivial due to several sources of uncertainty: dropouts due to "specular" reflections, obstacle location uncertainty due to the wide beam, and distance measurement error. Earlier papers address the latter problems, but dropouts remain a problem in many environments. We present an approach that lifts the overoptimistic independence assumption used in earlier work, and use Bayes nets to represent the dependencies between objects of the model. Objects of the model consist of readings, and of regions in which "quasi location invariance" of the (possible) obstacles exists, with respect to the readings. Simulation supports the method's feasibility. The model is readily extensible to allow for prior distributions, as well as other types of sensing operations.
National Conference on Artificial Intelligence, 2006
Research on preference elicitation and reasoning typically fo- cuses on preferences over single o... more Research on preference elicitation and reasoning typically fo- cuses on preferences over single objects of interest. However, in a number of applications the "outcomes" of interest are sets of such atomic objects. For instance, when creating the pro- gram for a film festival, editing a newspaper, or putting to- gether a team, we need to select a set of films
National Conference on Artificial Intelligence, 1997
The problem of counting the number of solutions to a constraint satisfaction problem (CSP) is rep... more The problem of counting the number of solutions to a constraint satisfaction problem (CSP) is rephrased in terms of probability updating in Bayes networks. Approximating the probabilities in Bayes networks is a problem which has been studied for a while, and may well provide a good approximation to counting the number of solutions. We use a simple approxima- tion based
Knowledge Discovery and Data Mining, 1998
FlexiMine is a KDD system designed as a testbed for data-mining research, as well as a generic kn... more FlexiMine is a KDD system designed as a testbed for data-mining research, as well as a generic knowledge discovery tool for varied database domains. Flexibil- ity is achieved by an open-ended design for extensi- bility, enabling integration of existing data-mining al- gorithms, new locally developed algorithms, and sup- port functions, such as visualization and preprocess- ing. Support for new databases
Journal of Experimental and Theoretical Artificial Intelligence, 1998
International Joint Conference on Artificial Intelligence, 2007
Recent scaling up of POMDP solvers towards re- alistic applications is largely due to point-based... more Recent scaling up of POMDP solvers towards re- alistic applications is largely due to point-based methods which quickly converge to an approximate solution for medium-sized problems. Of this family HSVI, which uses trial-based asynchronous value iteration, can handle the largest domains. In this paper we suggest a new algorithm, FSVI, that uses the underlying MDP to traverse the belief space
International Joint Conference on Artificial Intelligence, 2001
We present a new approach for personalized pre- sentation of web-page content. This approach is b... more We present a new approach for personalized pre- sentation of web-page content. This approach is based on preference-based constrained opti- mization techniques rooted in qualitative decision- theory. In our approach, web-page personalization is viewed as a configuration problem whose goal is to determine the optimal presentation of a web- page while taking into account the preferences of the web author,
In recent years, CP-nets have emerged as a useful tool for supporting preference elicitation, rea... more In recent years, CP-nets have emerged as a useful tool for supporting preference elicitation, reasoning, and representation. CP-nets capture and support reasoning with qualitative conditional preference statements, statements that are relatively natural for users to express. In this paper, we extend the CP-nets formalism to handle another class of very natural qualitative statements one often uses in expressing preferences in
The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2005
Computing optimal or approximate policies for partially observable Markov decision processes (POM... more Computing optimal or approximate policies for partially observable Markov decision processes (POMDPs) is a difficult task. When in addition the characteristics of the environment change over time, the problem is further compounded. A policy that was computed offline may stop being useful after sufficient changes to the environment have occurred. We present an online algorithm for incrementally improving POMDP policies, that is highly motivated by the Heuristic Search Value Iteration (HSVI) approach -locally improving the current value function after every action execution. Our algorithm adapts naturally to slow changes in the environment, without the need to explicitly model the changes. In initial empirical evaluation our algorithm shows a marked improvement over other online POMDP algorithms.
We are given: a directed graph G = ( y E); for each vertex u E V, a collection P(u) of sets of pr... more We are given: a directed graph G = ( y E); for each vertex u E V, a collection P(u) of sets of predecessors of U; and a target vertex t. Define a subset C of vertices to be complere if for each v E C there is some set Q E P(u) such that Q C C. We say that C is complete for t if in addition I E C. The problem is to find a parsimonious (minimal with respect to set-inclusion) set that is complete for f. This paper presents efficient algorithms for solving the problem, for general graphs and for acyclic ones. In the special case where G is acyclic, and has bounded in-degree, the algorithm presented has time complexity 0( IV/).
A max-2-connected Bayes network is one where there are at most 2 distinct directed paths between ... more A max-2-connected Bayes network is one where there are at most 2 distinct directed paths between any two nodes. We show that even for this restricted topology, null-evidence belief updating is hard to approximate.
Uncertainty Proceedings 1994, 1994
Independence-based (IB) assignments to Bayesian belief networks were originally proposed as abduc... more Independence-based (IB) assignments to Bayesian belief networks were originally proposed as abductive explanations. IB assignments assign fewer variables in abductive explanations than do schemes assigning values to all evidentially supported variables. We use IB assignments to approximate marginal probabilities in Bayesian belief networks. Recent work in belief updating for Bayes networks attempts to approximate posterior probabilities by nding a small number of the highest probability complete (or perhaps evidentially supported) assignments. Under certain assumptions, the probability mass in the union of these assignments is su cient to obtain a good approximation. Such methods are especially useful for highly-connected networks, where the maximum clique size or the cutset size make the standard algorithms intractable. Since IB assignments contain fewer assigned variables, the probability mass in each assignment is greater than in the respective complete assignment. Thus, fewer IB assignments are su cient, and a good approximation can be obtained more e ciently. IB assignments can be used for e ciently approximating posterior node probabilities even in cases which do not obey the rather strict skewness assumptions used in previous research. Two algorithms for nding the high probability IB assignments are suggested: one by doing a best-rst heuristic search, and another by special-purpose integer linear programming. Experimental results show that this approach is feasible for highly connected belief networks.
Lecture Notes in Computer Science, 2005
Learning to act in an unknown partially observable domain is a difficult variant of the reinforce... more Learning to act in an unknown partially observable domain is a difficult variant of the reinforcement learning paradigm. Research in the area has focused on model-free methods -methods that learn a policy without learning a model of the world. When sensor noise increases, model-free methods provide less accurate policies. The model-based approach -learning a POMDP model of the world, and computing an optimal policy for the learned model -may generate superior results in the presence of sensor noise, but learning and solving a model of the environment is a difficult problem. We have previously shown how such a model can be obtained from the learned policy of model-free methods, but this approach implies a distinction between a learning phase and an acting phase that is undesirable. In this paper we present a novel method for learning a POMDP model online, based on McCallums' Utile Suffix Memory (USM), in conjunction with an approximate policy obtained using an incremental POMDP solver. We show that the incrementally improving policy provides superior results to the original USM algorithm, especially in the presence of increasing sensor and action noise.
2008 IEEE 25th Convention of Electrical and Electronics Engineers in Israel, 2008
2002 IEEE International Conference on Data Mining, 2002. Proceedings., 2002
Abstract Whereas data mining in structured data focuses on frequent data values, in semistructure... more Abstract Whereas data mining in structured data focuses on frequent data values, in semistructured and graph data the emphasis is on frequent labels and common topologies. Here, the structure of the data is just as important as its content. We study the problem of ...
ACM Transactions on Information Systems, 2004
We present a new approach for adaptive presentation of structured information, based on preferenc... more We present a new approach for adaptive presentation of structured information, based on preference-based constrained optimization techniques rooted in qualitative decision-theory. In this approach, document presentation is viewed as a configuration problem whose goal is to determine the optimal presentation of a document, while taking into account the preferences of the content provider, viewer interaction with the browser, and, possibly,
Workshop on Rich …, 2005
Agents learning to act in a partially observable domain may need to overcome the problem of noisy... more Agents learning to act in a partially observable domain may need to overcome the problem of noisy output from the agent's sensors. Research in the area has focused on model-free methods—methods that learn a policy without learning a model of the world. ...
Journal of Computer and System Sciences, 2012
iMatch is a probabilistic scheme for ontology matching based on Markov networks, which has severa... more iMatch is a probabilistic scheme for ontology matching based on Markov networks, which has several advantages over other probabilistic schemes. First, it uses undirected networks, which better supports the non-causal nature of the dependencies. Second, it handles the high computational complexity by doing approximate reasoning, rather then by ad-hoc pruning. Third, the probabilities that it uses are learned from matched data. Finally, iMatch naturally supports interactive semiautomatic matches. Experiments using the standard benchmark tests that compare our approach with the most promising existing systems show that iMatch is one of the top performers. * Supported by the IMG4 consortium under the MAGNET program of the Israel ministry of trade and industry; and the Lynn and William Frankel center for computer science.
International Journal of Approximate Reasoning, 1997
Belief updating in Bayes nets, a well known computationally hard problem, has recently been appro... more Belief updating in Bayes nets, a well known computationally hard problem, has recently been approximated by several deterministic algorithms, and by various randomized approximation algorithms. Deterministic algorithms usually provide probability bounds, but have an exponential runtime. Some randomized schemes have a polynomial runtime, but provide only probability estimates.
International Journal of Approximate Reasoning, 2003
New knowledge is incrementally introduced to an existing knowledge base in a typical knowledge-en... more New knowledge is incrementally introduced to an existing knowledge base in a typical knowledge-engineering cycle. Unfortunately, at most given stages, the knowledge-base is incomplete but must still satisfy sufficient consistency conditions in order to provide sound semantics. Maintaining semantics for uncertainty is of primary concern. We examine Bayesian knowledge bases (BKBs), which are a generalization of Bayesian networks. BKBs provide a highly flexible and intuitive representation following a basic ''if-then'' structure in conjunction with probability theory. We present new theoretical and algorithmic results concerning BKBs and how they can naturally and implicitly preserve semantics as new knowledge is added. In particular, equivalence of rule weights and conditional probabilities is achieved through stability of inferencing in BKBs. Furthermore, efficient algorithms are developed to guarantee stability of BKBs during construction. Finally, we examine and prove formal conditions that hold during the incremental construction of BKBs.
Uploads
Papers by Solomon Shimony