{"ID":2891873,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16881","arxiv_id":"2507.16881","title":"Confidence Optimization for Probabilistic Encoding","abstract":"Probabilistic encoding introduces Gaussian noise into neural networks, enabling a smooth transition from deterministic to uncertain states and enhancing generalization ability. However, the randomness of Gaussian noise distorts point-based distance measurements in classification tasks. To mitigate this issue, we propose a confidence optimization probabilistic encoding (CPE) method that improves distance reliability and enhances representation learning. Specifically, we refine probabilistic encoding with two key strategies: First, we introduce a confidence-aware mechanism to adjust distance calculations, ensuring consistency and reliability in probabilistic encoding classification tasks. Second, we replace the conventional KL divergence-based variance regularization, which relies on unreliable prior assumptions, with a simpler L2 regularization term to directly constrain variance. The method we proposed is model-agnostic, and extensive experiments on natural language classification tasks demonstrate that our method significantly improves performance and generalization on both the BERT and the RoBERTa model.","short_abstract":"Probabilistic encoding introduces Gaussian noise into neural networks, enabling a smooth transition from deterministic to uncertain states and enhancing generalization ability. However, the randomness of Gaussian noise distorts point-based distance measurements in classification tasks. To mitigate this issue, we propos...","url_abs":"https://arxiv.org/abs/2507.16881","url_pdf":"https://arxiv.org/pdf/2507.16881v1","authors":"[\"Pengjiu Xia\",\"Yidian Huang\",\"Wenchao Wei\",\"Yuwen Tan\"]","published":"2025-07-22T15:32:27Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}