Search Results for author:
Found 11 papers, 3 papers with code
SPFQ: A Stochastic Algorithm and Its Error Analysis for Neural Network Quantization
Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks.
A simple approach for quantizing neural networks
In this short note, we propose a new method for quantizing the weights of a fully trained neural network.
Spectrally Adaptive Common Spatial Patterns
In this work, we propose a novel algorithm called Spectrally Adaptive Common Spatial Patterns (SACSP) that improves CSP by learning a temporal/spectral filter for each spatial filter so that the spatial filters are concentrated on the most relevant temporal frequencies for each user.
Post-training Quantization for Neural Networks with Provable Guarantees
Additionally, our error analysis expands the results of previous work on GPFQ to handle general quantization alphabets, showing that for quantizing a single-layer network, the relative square error essentially decays linearly in the number of weights -- i. e., level of over-parametrization.
Sigma-Delta and Distributed Noise-Shaping Quantization Methods for Random Fourier Features
We propose the use of low bit-depth Sigma-Delta and distributed noise-shaping methods for quantizing the Random Fourier features (RFFs) associated with shift-invariant kernels.
A Greedy Algorithm for Quantizing Neural Networks
This simple algorithm is equivalent to running a dynamical system, which we prove is stable for quantizing a single-layer neural network (or, alternatively, for quantizing the first layer of a multi-layer network) when the training data are Gaussian.
Faster Binary Embeddings for Preserving Euclidean Distances
When $\mathcal{T}$ consists of well-spread (i. e., non-sparse) vectors, our embedding method applies a stable noise-shaping quantization scheme to $A x$ where $A\in\mathbb{R}^{m\times n}$ is a sparse Gaussian random matrix.
Random Vector Functional Link Networks for Function Approximation on Manifolds
We provide a (corrected) rigorous proof that the Igelnik and Pao construction is a universal approximator for continuous functions on compact domains, with approximation error decaying asymptotically like $O(1/\sqrt{n})$ for the number $n$ of network nodes.
Fast binary embeddings, and quantized compressed sensing with structured matrices
Our methods rely on quantizing fast Johnson-Lindenstrauss embeddings based on bounded orthonormal systems and partial circulant ensembles, both of which admit fast transforms.
Simple Classification using Binary Data
Binary, or one-bit, representations of data arise naturally in many applications, and are appealing in both hardware implementations and algorithm design.
One-bit compressive sensing with norm estimation
Consider the recovery of an unknown signal ${x}$ from quantized linear measurements.
