Minimax Rates for Statistical Inverse Problems Under General Source Conditions

被引:7
作者
Ding, Litao [1 ]
Mathe, Peter [2 ]
机构
[1] Fudan Univ, Sch Math Sci, Shanghai 200433, Peoples R China
[2] Weierstrass Inst, Mohrenstr 39, D-10117 Berlin, Germany
基金
中国国家自然科学基金;
关键词
Statistical Inverse Problem; General Source Condition; Minimax Rate; ILL-POSED PROBLEMS; HILBERT SCALES; REGULARIZATION;
D O I
10.1515/cmam-2017-0055
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
We describe the minimax reconstruction rates in linear ill-posed equations in Hilbert space when smoothness is given in terms of general source sets. The underlying fundamental result, the minimax rate on ellipsoids, is proved similarly to the seminal study by D. L. Donoho, R. C. Liu, and B. MacGibbon [4]. These authors highlighted the special role of the truncated series estimator, and for such estimators the risk can explicitly be given. We provide several examples, indicating results for statistical estimation in ill-posed problems in Hilbert space.
引用
收藏
页码:603 / 608
页数:6
相关论文
共 10 条
[1]   Convergence rates of general regularization methods for statistical inverse problems and applications [J].
Bissantz, N. ;
Hohage, T. ;
Munk, A. ;
Ruymgaart, F. .
SIAM JOURNAL ON NUMERICAL ANALYSIS, 2007, 45 (06) :2610-2636
[2]   Nonparametric statistical inverse problems [J].
Cavalier, L. .
INVERSE PROBLEMS, 2008, 24 (03)
[3]  
Donoho D. L., 1988, 123 U CAL DEP STAT
[4]   MINIMAX RISK OVER HYPERRECTANGLES, AND IMPLICATIONS [J].
DONOHO, DL ;
LIU, RC ;
MACGIBBON, B .
ANNALS OF STATISTICS, 1990, 18 (03) :1416-1437
[5]   Non asymptotic minimax rates of testing in signal detection with heterogeneous variances [J].
Laurent, Beatrice ;
Loubes, Jean-Michel ;
Marteau, Clement .
ELECTRONIC JOURNAL OF STATISTICS, 2012, 6 :91-122
[6]  
Loubes J.-M., 2009, INT J TOMOGRAPHY STA, V11, P61
[7]   Statistical inverse estimation in Hilbert scales [J].
Mair, BA ;
Ruymgaart, FH .
SIAM JOURNAL ON APPLIED MATHEMATICS, 1996, 56 (05) :1424-1444
[8]   Geometry of linear ill-posed problems in variable Hilbert scales [J].
Mathé, P ;
Pereverzev, SV .
INVERSE PROBLEMS, 2003, 19 (03) :789-803
[9]   Regularization of some linear ill-posed problems with discretized random noisy data [J].
Mathe, Peter ;
Pereverzev, Sergei V. .
MATHEMATICS OF COMPUTATION, 2006, 75 (256) :1913-1929
[10]  
Pinsker M. S., 1980, Problems of Information Transmission, V16, P120