Online Least Squares Estimation with Self-Normalized Processes: An Application to Bandit Problems

Some aspects of the sequential design of experiments

H. Robbins · 1952

Earlier work this paper cites.

Boundary crossing probabilities for the Wiener process and sample sums

H. Robbins and D. Siegmund · 1970

Earlier work this paper cites.

On tail probabilities for martingales

D.A. Freedman · 1975

Earlier work this paper cites.

Strong consistency of least squares estimates in multiple regression

T.L. Lai, H. Robbins, and C.Z. Wei · 1979

Earlier work this paper cites.

Least squares estimates in stochastic regression models with applications to identification and control of dynamic systems

T.L. Lai and C.Z. Wei · 1982

Earlier work this paper cites.

Asymptotically efficient adaptive allocation rules

T. L. Lai and H. Robbins · 1985

Earlier work this paper cites.

Matrix Perturbation Theory

G.W. Stewart and Ji-guang Sun · 1990

Cited alongside, same era.

Finite time analysis of the multiarmed bandit problem

P. Auer, N. Cesa-Bianchi, and P. Fischer · 2002

Cited alongside, same era.

Using confidence bounds for exploitation-exploration trade-offs

Peter Auer · 2003

Cited alongside, same era.

Self-normalized processes: exponential inequalities, moment bounds and iterated logarithm laws

V.H. de la Peña, M.J. Klass, and T.L. Lai · 2004

Cited alongside, same era.

Prediction, Learning, and Games

N. Cesa-Bianchi and G. Lugosi · 2006

Cited alongside, same era.

Online optimization in X-armed bandits

S. Bubeck, R. Munos, G. Stoltz, and Cs. Szepesvári · 2008

Cited alongside, same era.

Stochastic linear optimization under bandit feedback

V. Dani, T.P. Hayes, and S.M. Kakade · 2008

Later among the works it cites.

On upper-confidence bound policies for non-stationary bandit problems

Original

A Garivier and E Moulines · 2008

Later among the works it cites.

Self-normalized processes: Limit theory and Statistical Applications

V.H. de la Peña, T.L. Lai, and Q.-M. Shao · 2009

Later among the works it cites.

Active learning in heteroscedastic noise

A. Antos, V. Grover, and Cs. Szepesvári · 2010

Later among the works it cites.

Linearly parameterized bandits

P. Rusmevichientong and J.N. Tsitsiklis · 2010

Later among the works it cites.