Soft Quantization using Entropic Regularization
This work addresses the quantization problem in probability theory and machine learning, offering a robust method for approximation tasks, though it appears incremental as it builds on existing entropy-regularized techniques.
The paper tackles the quantization problem of approximating probability measures with discrete ones using Wasserstein distance, by introducing an entropy-regularized relaxation that employs a softmin function and a stochastic gradient approach for optimization, with empirical demonstrations of its performance.
The quantization problem aims to find the best possible approximation of probability measures on ${\mathbb{R}}^d$ using finite, discrete measures. The Wasserstein distance is a typical choice to measure the quality of the approximation. This contribution investigates the properties and robustness of the entropy-regularized quantization problem, which relaxes the standard quantization problem. The proposed approximation technique naturally adopts the softmin function, which is well known for its robustness in terms of theoretical and practicability standpoints. Moreover, we use the entropy-regularized Wasserstein distance to evaluate the quality of the soft quantization problem's approximation, and we implement a stochastic gradient approach to achieve the optimal solutions. The control parameter in our proposed method allows for the adjustment of the optimization problem's difficulty level, providing significant advantages when dealing with exceptionally challenging problems of interest. As well, this contribution empirically illustrates the performance of the method in various expositions.