D
David L. Donoho
Researcher at Stanford University
Publications - 273
Citations - 115802
David L. Donoho is an academic researcher from Stanford University. The author has contributed to research in topics: Wavelet & Compressed sensing. The author has an hindex of 110, co-authored 271 publications receiving 108027 citations. Previous affiliations of David L. Donoho include University of California, Berkeley & Western Geophysical.
Papers
More filters
Journal ArticleDOI
On the stability of the basis pursuit in the presence of noise
David L. Donoho,Michael Elad +1 more
TL;DR: This paper establishes here the stability of the BP in the presence of noise for sparse enough representations, and is a direct generalization of noiseless BP study, and indeed, when the noise power is reduced to zero, the known results of the noisless BP are obtained.
Journal ArticleDOI
Prevalence of neural collapse during the terminal phase of deep learning training.
TL;DR: A now-standard training methodology: driving the cross-entropy loss to zero, continuing long after the classification error is already zero, is considered, helping to understand an important component of the modern deep learning training paradigm.
Book
Multiscale representations for manifold-valued data
TL;DR: Multiscale representations for data observed on equispaced grids and taking values in manifolds such as the sphere, the special orthogonal group, the positive definite matrices, and the Grassmann manifolds, using theExp and Log maps of those manifolds are described.
Journal ArticleDOI
Signal recovery and the large sieve
David L. Donoho,B. F. Logan +1 more
TL;DR: Inequalities are developed for the fraction of a bandlimited function’s $L_p $ norm that can be concentrated on any set of small “Nyquist density” so that a wideband signal supported on a set of Nyquist density can be reconstructed stably from noisy data, even when the low-frequency information is completely missing.
Journal ArticleDOI
Minimax risk over l p -balls for l p -error
TL;DR: In this article, it was shown that the ratio of minimax linear risk to minimax risk can be asymptotically minimax at small signal-to-noise ratios, and within a bounded factor of asymPTotic minimaxity in general.