Iteratively Training Look-Up Tables for Network Quantization
This work addresses the need for efficient neural network deployment on limited hardware, offering a versatile solution, though it appears incremental as it builds on existing quantization and pruning techniques.
The authors tackled the problem of reducing memory and computational footprint of deep neural networks for resource-constrained devices by proposing Look-Up Table Quantization (LUT-Q), a flexible framework that learns value dictionaries and assignment matrices to represent weights, enabling various reduction methods like non-uniform quantization and pruning without solver changes.
Operating deep neural networks (DNNs) on devices with limited resources requires the reduction of their memory as well as computational footprint. Popular reduction methods are network quantization or pruning, which either reduce the word length of the network parameters or remove weights from the network if they are not needed. In this article we discuss a general framework for network reduction which we call `Look-Up Table Quantization` (LUT-Q). For each layer, we learn a value dictionary and an assignment matrix to represent the network weights. We propose a special solver which combines gradient descent and a one-step k-means update to learn both the value dictionaries and assignment matrices iteratively. This method is very flexible: by constraining the value dictionary, many different reduction problems such as non-uniform network quantization, training of multiplierless networks, network pruning or simultaneous quantization and pruning can be implemented without changing the solver. This flexibility of the LUT-Q method allows us to use the same method to train networks for different hardware capabilities.