Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If you need an accessible version of this item please contact JSTOR User Support

Convergence of Algorithms for Reconstructing Convex Bodies and Directional Measures

Richard J. Gardner, Markus Kiderlen and Peyman Milanfar
The Annals of Statistics
Vol. 34, No. 3 (Jun., 2006), pp. 1331-1374
Stable URL: http://www.jstor.org/stable/25463460
Page Count: 44
  • Get Access
  • Read Online (Free)
  • Download ($19.00)
  • Cite this Item
If you need an accessible version of this item please contact JSTOR User Support
Convergence of Algorithms for Reconstructing Convex Bodies and Directional Measures
Preview not available

Abstract

We investigate algorithms for reconstructing a convex body K in ${\Bbb R}^{n}$ from noisy measurements of its support function or its brightness function in k directions $u_{1},\ldots ,u_{k}$. The key idea of these algorithms is to construct a convex polytope $P_{k}$ whose support function (or brightness function) best approximates the given measurements in the directions $u_{1},\ldots ,u_{k}$ (in the least squares sense). The measurement errors are assumed to be stochastically independent and Gaussian. It is shown that this procedure is (strongly) consistent, meaning that, almost surely, $P_{k}$ tends to K in the Hausdorff metric as k → ∞. Here some mild assumptions on the sequence $(u_{i})$ of directions are needed. Using results from the theory of empirical processes, estimates of rates of convergence are derived, which are first obtained in the L₂ metric and then transferred to the Hausdorff metric. Along the way, a new estimate is obtained for the metric entropy of the class of origin-symmetric zonoids contained in the unit ball. Similar results are obtained for the convergence of an algorithm that reconstructs an approximating measure to the directional measure of a stationary fiber process from noisy measurements of its rose of intersections in k directions $u_{1},\ldots ,u_{k}$. Here the Dudley and Prohorov metrics are used. The methods are linked to those employed for the support and brightness function algorithms via the fact that the rose of intersections is the support function of a projection body.

Page Thumbnails

  • Thumbnail: Page 
1331
    1331
  • Thumbnail: Page 
1332
    1332
  • Thumbnail: Page 
1333
    1333
  • Thumbnail: Page 
1334
    1334
  • Thumbnail: Page 
1335
    1335
  • Thumbnail: Page 
1336
    1336
  • Thumbnail: Page 
1337
    1337
  • Thumbnail: Page 
1338
    1338
  • Thumbnail: Page 
1339
    1339
  • Thumbnail: Page 
1340
    1340
  • Thumbnail: Page 
1341
    1341
  • Thumbnail: Page 
1342
    1342
  • Thumbnail: Page 
1343
    1343
  • Thumbnail: Page 
1344
    1344
  • Thumbnail: Page 
1345
    1345
  • Thumbnail: Page 
1346
    1346
  • Thumbnail: Page 
1347
    1347
  • Thumbnail: Page 
1348
    1348
  • Thumbnail: Page 
1349
    1349
  • Thumbnail: Page 
1350
    1350
  • Thumbnail: Page 
1351
    1351
  • Thumbnail: Page 
1352
    1352
  • Thumbnail: Page 
1353
    1353
  • Thumbnail: Page 
1354
    1354
  • Thumbnail: Page 
1355
    1355
  • Thumbnail: Page 
1356
    1356
  • Thumbnail: Page 
1357
    1357
  • Thumbnail: Page 
1358
    1358
  • Thumbnail: Page 
1359
    1359
  • Thumbnail: Page 
1360
    1360
  • Thumbnail: Page 
1361
    1361
  • Thumbnail: Page 
1362
    1362
  • Thumbnail: Page 
1363
    1363
  • Thumbnail: Page 
1364
    1364
  • Thumbnail: Page 
1365
    1365
  • Thumbnail: Page 
1366
    1366
  • Thumbnail: Page 
1367
    1367
  • Thumbnail: Page 
1368
    1368
  • Thumbnail: Page 
1369
    1369
  • Thumbnail: Page 
1370
    1370
  • Thumbnail: Page 
1371
    1371
  • Thumbnail: Page 
1372
    1372
  • Thumbnail: Page 
1373
    1373
  • Thumbnail: Page 
1374
    1374