On Model Compression for Neural Networks: Framework, Algorithm, and Convergence Guarantee
This work addresses model compression for deploying neural networks in memory-limited devices, offering a novel optimization approach with theoretical guarantees, but it is incremental as it builds on existing compression techniques.
The paper tackles the problem of accuracy loss and convergence issues in neural network model compression via low-rank approximation and weight pruning, proposing a nonconvex optimization framework and an algorithm that achieves global convergence at a rate of O(1/k) with superior performance in experiments.
Model compression is a crucial part of deploying neural networks (NNs), especially when the memory and storage of computing devices are limited in many applications. This paper focuses on two model compression techniques: low-rank approximation and weight pruning in neural networks, which are very popular nowadays. However, training NN with low-rank approximation and weight pruning always suffers significant accuracy loss and convergence issues. In this paper, a holistic framework is proposed for model compression from a novel perspective of nonconvex optimization by designing an appropriate objective function. Then, we introduce NN-BCD, a block coordinate descent (BCD) algorithm to solve the nonconvex optimization. One advantage of our algorithm is that an efficient iteration scheme can be derived with closed-form, which is gradient-free. Therefore, our algorithm will not suffer from vanishing/exploding gradient problems. Furthermore, with the Kurdyka-Łojasiewicz (KŁ) property of our objective function, we show that our algorithm globally converges to a critical point at the rate of O(1/k), where k denotes the number of iterations. Lastly, extensive experiments with tensor train decomposition and weight pruning demonstrate the efficiency and superior performance of the proposed framework. Our code implementation is available at https://github.com/ChenyangLi-97/NN-BCD