Frame quantization of neural networks
From MaRDI portal
Cites work
- A greedy algorithm for quantizing neural networks
- A simple approach for quantizing neural networks
- Approximating a bandlimited function using very coarsely quantized data: a family of stable sigma-delta modulators of arbitrary order
- Approximating a bandlimited function using very coarsely quantized data: Improved error estimates in sigma-delta modulation
- BinaryRelax: a relaxation approach for training deep neural networks with quantized weights
- Complex sigma-delta quantization algorithms for finite frames
- Frame paths and error bounds for sigma-delta quantization
- Linear Perturbations of the Wigner Transform and the Weyl Quantization
- Localization of frames, Banach frames, and the invertibility of the frame operator
- Loss aware post-training quantization
- One-bit sigma-delta quantization with exponential accuracy
- Pointwise comparison of PCM and \(\Sigma \Delta \) quantization
- Post-training Quantization for Neural Networks with Provable Guarantees
- Quantization of compressive samples with stable and robust recovery
- Recurrence of optimum for training weight and activation quantized networks
- Second-order sigma-delta (\(\Sigma \Delta\)) quantization of finite frame expansions
- Sigma-delta (/spl Sigma//spl Delta/) quantization and finite frames
- Sigma-Delta and Distributed Noise-Shaping Quantization Methods for Random Fourier Features
- Sigma-delta quantization errors and the traveling salesman problem
- Sigma-Delta quantization of sub-Gaussian frame expansions and its application to compressed sensing
- Sobolev duals for random frames and \(\varSigma \varDelta \) quantization of compressed sensing measurements
- Time-frequency analysis of localization operators.
- Time-frequency localization operators and a Berezin transform
Cited in
(1)
This page was built for publication: Frame quantization of neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6928763)
