Results 31 to 38 of about 259 (38)

Bounded regret in stochastic multi-armed bandits

, 2013
We study the stochastic multi-armed bandit problem when one knows the value $\mu^{(\star)}$ of an optimal arm, as a well as a positive lower bound on the smallest positive gap $\Delta$.
Bubeck, Sébastien, Perchet, Vianney, Rigollet, Philippe   +2 more
core  

Online learning in repeated auctions

, 2015
Motivated by online advertising auctions, we consider repeated Vickrey auctions where goods of unknown value are sold sequentially and bidders only learn (potentially noisy) information about a good's value once it is purchased.
Perchet, Vianney, Rigollet, Philippe, Weed, Jonathan   +2 more
core   +1 more source

MODEL ASSISTED VARIABLE CLUSTERING: MINIMAX-OPTIMAL RECOVERY AND ALGORITHMS. [PDF]

Ann Stat, 2020
Bunea F, Giraud C, Luo X, Royer M, Verzelen N.   +4 more
europepmc   +1 more source

"Minimax Multivariate Empirical Bayes Estimators under Multicollinearity" [PDF]

In this paper we consider the problem of estimating the matrix of regression coefficients in a multivariate linear regression model in which the design matrix is near singular.
M. S. Srivastava, Tatsuya Kubokawa
core  

Multiperiod Maximum Loss is time unit invariant. [PDF]

Springerplus, 2016
Kovacevic RM, Breuer T.
europepmc   +1 more source

I-LAMM FOR SPARSE LEARNING: SIMULTANEOUS CONTROL OF ALGORITHMIC COMPLEXITY AND STATISTICAL ERROR. [PDF]

Ann Stat, 2018
Fan J, Liu H, Sun Q, Zhang T.
europepmc   +1 more source

EXACT MINIMAX ESTIMATION OF THE PREDICTIVE DENSITY IN SPARSE GAUSSIAN MODELS. [PDF]

Ann Stat, 2015
Mukherjee G, Johnstone IM.
europepmc   +1 more source

REINFORCEMENT LEARNING FOR INDIVIDUAL OPTIMAL POLICY FROM HETEROGENEOUS DATA. [PDF]

Ann Stat
Miao BR, Shahbaba B, Qu A.
europepmc   +1 more source