10.9k citations
- SLAC National Accelerator LaboratoryUS411 papers
- Kavli Institute for Particle Astrophysics and CosmologyUS307 papers
- Centre National de la Recherche ScientifiqueFR166 papers
- University of California, BerkeleyUS166 papers
- California Institute of TechnologyUS162 papers
- Massachusetts Institute of TechnologyUS144 papers
- University of California, Santa CruzUS135 papers
- Stanford Synchrotron Radiation LightsourceUS128 papers
- Lawrence Berkeley National LaboratoryUS126 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR121 papers
- University of Maryland, College ParkUS119 papers
- Université Paris CitéFR114 papers
97 papers · 1 filter
Deep Knowledge Tracing
Chris Piech, Jonathan Spencer, Jonathan Huang +4
Knowledge tracing---where a machine models the knowledge of a student as they interact with coursework---is a well established problem in computer supported education. Though effec…
Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach
Yinlam Chow, Aviv Tamar, Shie Mannor +1
In this paper we address the problem of decision making within a Markov decision process (MDP) framework where risk and modeling errors are taken into account. Our approach is to m…
Policy Gradient for Coherent Risk Measures
Aviv Tamar, Yinlam Chow, Mohammad Ghavamzadeh +1
Several authors have recently developed risk-sensitive policy gradient methods that augment the standard expected cost minimization problem with a measure of variability in cost. T…
RoboBrain: Large-Scale Knowledge Engine for Robots
Ashutosh Saxena, Ashesh Jain, Ozan Sener +3
In this paper we introduce a knowledge engine, which learns and shares knowledge representations, for robots to carry out a variety of tasks. Building such an engine brings with it…
Pattern Decomposition with Complex Combinatorial Constraints: Application to Materials Discovery
Stefano Ermon, Ronan Le Bras, Santosh K. Suram +4
Identifying important components or factors in large amounts of noisy data is a key problem in machine learning and data mining. Motivated by a pattern decomposition problem in mat…
Predicting the behavior of interacting humans by fusing data from multiple sources
Erik J. Schlicht, Ritchie Lee, David H. Wolpert +2
Multi-fidelity methods combine inexpensive low-fidelity simulations with costly but highfidelity simulations to produce an accurate model of a system of interest at minimal cost. T…