Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.11868 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910876839182336 |
|---|---|
| author | Mehraban, Zahra Pichler, Alois |
| author_facet | Mehraban, Zahra Pichler, Alois |
| contents | Accurate approximation of probability measures is essential in numerical applications. This paper explores the quantization of probability measures using the maximum mean discrepancy (MMD) distance as a guiding metric. We first investigate optimal approximations by determining the best weights, followed by addressing the problem of optimal facility locations.
To facilitate efficient computation, we reformulate the nonlinear objective as expectations over a product space, enabling the use of stochastic approximation methods. For the Gaussian kernel, we derive closed-form expressions to develop a deterministic optimization approach. By integrating stochastic approximation with deterministic techniques, our framework achieves precise and efficient quantization of continuous distributions, with significant implications for machine learning and signal processing applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11868 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantization Of Probability Measures In Maximum~Mean~Discrepancy Distance Mehraban, Zahra Pichler, Alois Optimization and Control Accurate approximation of probability measures is essential in numerical applications. This paper explores the quantization of probability measures using the maximum mean discrepancy (MMD) distance as a guiding metric. We first investigate optimal approximations by determining the best weights, followed by addressing the problem of optimal facility locations. To facilitate efficient computation, we reformulate the nonlinear objective as expectations over a product space, enabling the use of stochastic approximation methods. For the Gaussian kernel, we derive closed-form expressions to develop a deterministic optimization approach. By integrating stochastic approximation with deterministic techniques, our framework achieves precise and efficient quantization of continuous distributions, with significant implications for machine learning and signal processing applications. |
| title | Quantization Of Probability Measures In Maximum~Mean~Discrepancy Distance |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2503.11868 |