Two randomized Hadamard transforms suffice to make coordinate marginals O(d^{-1/2})-close to Gaussian for most quantization methods, with three needed for vector quantization to match uniform random rotations asymptotically.
US Government printing office, 1948
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Stochastic generalized sampling uses leverage-score sampling and a new matrix Bernstein inequality to guarantee stable recovery at m ≳ n log n samples with high probability, even for redundant frames, and demonstrates near-exponential convergence on analytic function recovery from Fourier data.
New DG methods for gKdV and HS-KdV that preserve multiple invariants via implicit penalization, allowing high-order time accuracy.
citing papers explorer
-
Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
Two randomized Hadamard transforms suffice to make coordinate marginals O(d^{-1/2})-close to Gaussian for most quantization methods, with three needed for vector quantization to match uniform random rotations asymptotically.
-
Stochastic Generalized Sampling
Stochastic generalized sampling uses leverage-score sampling and a new matrix Bernstein inequality to guarantee stable recovery at m ≳ n log n samples with high probability, even for redundant frames, and demonstrates near-exponential convergence on analytic function recovery from Fourier data.
-
High-order Conservative Discontinuous Galerkin Methods via Implicit Penalization for the Generalized Korteweg-de Vries Equation and the Hirota-Satsuma KdV System
New DG methods for gKdV and HS-KdV that preserve multiple invariants via implicit penalization, allowing high-order time accuracy.