The following pages link to Gilles Stoltz (Q366994):
Displayed 29 items.
- Kullback-Leibler upper confidence bounds for optimal sequential allocation (Q366995) (← links)
- A primal condition for approachability with partial monitoring (Q482547) (← links)
- Forecasting electricity consumption by aggregating specialized experts (Q1945028) (← links)
- Sequential model aggregation for production forecasting (Q2009841) (← links)
- Fano's inequality for random variables (Q2218038) (← links)
- Learning correlated equilibria in games with compact sets of strategies (Q2371157) (← links)
- Improved second-order bounds for prediction with expert advice (Q2384131) (← links)
- Pure exploration in finitely-armed and continuous-armed bandits (Q2431430) (← links)
- (Q2934107) (← links)
- Lipschitz Bandits without the Lipschitz Constant (Q3093946) (← links)
- Strategies for Prediction Under Imperfect Monitoring (Q3168980) (← links)
- A Geometric Proof of Calibration (Q3169115) (← links)
- Minimizing Regret With Label Efficient Prediction (Q3546663) (← links)
- (Q3549885) (← links)
- Pure Exploration in Multi-armed Bandits Problems (Q3648740) (← links)
- Learning Theory (Q4680917) (← links)
- (Q5169876) (← links)
- Explore First, Exploit Next: The True Shape of Regret in Bandit Problems (Q5219722) (← links)
- (Q5263253) (← links)
- Learning Theory and Kernel Machines (Q5305866) (← links)
- Regret Minimization Under Partial Monitoring (Q5387997) (← links)
- (Q5396654) (← links)
- Strategies for Prediction Under Imperfect Monitoring (Q5434054) (← links)
- Learning Theory (Q5473612) (← links)
- Internal regret in on-line portfolio selection (Q5916205) (← links)
- Internal regret in on-line portfolio selection (Q5921688) (← links)
- Pure Exploration for Multi-Armed Bandit Problems (Q6208466) (← links)
- A Finite-Time Analysis of Multi-armed Bandits Problems with Kullback-Leibler Divergences (Q6225697) (← links)
- Fano's inequality for random variables (Q6283393) (← links)