Universal nonadaptive algorithms recover anisotropic Sobolev functions near-optimally via compressed sensing on Fourier coefficients, while linear methods suffer dimension-dependent polylog penalties.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.NA 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Universal, sample-optimal algorithms for recovery of anisotropic functions from i.i.d. samples
Universal nonadaptive algorithms recover anisotropic Sobolev functions near-optimally via compressed sensing on Fourier coefficients, while linear methods suffer dimension-dependent polylog penalties.