Sciweavers

COLT
2010
Springer
13 years 8 months ago
Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback
Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially gen...
Alekh Agarwal, Ofer Dekel, Lin Xiao
AI
2006
Springer
13 years 10 months ago
Constraint-based optimization and utility elicitation using the minimax decision criterion
In many situations, a set of hard constraints encodes the feasible configurations of some system or product over which multiple users have distinct preferences. However, making su...
Craig Boutilier, Relu Patrascu, Pascal Poupart, Da...
IJCAI
2003
13 years 11 months ago
Incremental Utility Elicitation with the Minimax Regret Decision Criterion
Utility elicitation is a critical function of any automated decision aid, allowing decisions to be tailored to the preferences of a specific user. However, the size and complexit...
Tianhan Wang, Craig Boutilier
AAAI
2010
13 years 11 months ago
Robust Policy Computation in Reward-Uncertain MDPs Using Nondominated Policies
The precise specification of reward functions for Markov decision processes (MDPs) is often extremely difficult, motivating research into both reward elicitation and the robust so...
Kevin Regan, Craig Boutilier
CDC
2009
IEEE
169views Control Systems» more  CDC 2009»
14 years 2 months ago
Parametric regret in uncertain Markov decision processes
— We consider decision making in a Markovian setup where the reward parameters are not known in advance. Our performance criterion is the gap between the performance of the best ...
Huan Xu, Shie Mannor
SIGECOM
2010
ACM
183views ECommerce» more  SIGECOM 2010»
14 years 2 months ago
Assessing regret-based preference elicitation with the UTPREF recommendation system
Product recommendation and decision support systems must generally develop a model of user preferences by querying or otherwise interacting with a user. Recent approaches to elici...
Darius Braziunas, Craig Boutilier
RECSYS
2009
ACM
14 years 4 months ago
Preference elicitation with subjective features
Utility or preference elicitation is a critical component in many recommender and decision support systems. However, most frameworks for elicitation assume a predefined set of fe...
Craig Boutilier, Kevin Regan, Paolo Viappiani