We derive analytic bounds on the noise invariance of majority vote classifiers operating on compressed inputs. Specifically, starting from recent bounds on the true risk of majority vote classifiers, we extend the applicability of PAC-Bayesian theory to quantify the resilience of majority votes to input noise stemming from compression. The derived bounds are intuitive in binary classification settings, where they can be measured as expressions of voter differentials and voter pair agreement. By combining measures of input distortion with analytic guarantees on noise invariance, we prescribe rate-efficient machines to compress inputs without affecting subsequent classification. Our validation shows how bounding noise invariance can inform the compression stage for any majority vote classifier such that worst-case implications of bad input reconstructions are known, and inputs can be compressed to the minimum amount of information needed prior to inference.翻译

我们推导出多数投票分类器在处理压缩输入时的噪声不变性的解析界限。具体来说，从最近关于多数投票分类器真实风险的界限出发，我们扩展了PAC-Bayesian理论的适用性，以量化多数投票对来自压缩的输入噪声的抵抗能力。这些导出的界限在二元分类设置中具有直观性，可以通过选民差异和选民对一致性的表达式来衡量。通过将输入失真度量与噪声不变性的解析保证相结合，我们可以指定有效率的机器来压缩输入，而不影响后续的分类。我们的验证表明，通过界定噪声不变性，可以为任何多数投票分类器的压缩阶段提供信息，以便在知道恶劣输入重构的最坏情况下，将输入压缩到推理所需的最小信息量。

相关问题

In this correspondence we derive a STSA estimator which minimizes the mean-square error of the log-spectra (i.e., the original STSA and its estimator) and examine it in enhancing noisy speech. -We found that this estimator is superior to the MMSE STSA estimator derived in [ 11 since it results in a much lower residual noise level without further affecting the speech itself. In fact, the new estimator results in a very similar enhanced speech quality as that obtained with the MMSE STSA estimator of [ 11, which takes into account the signal presence uncertainty.翻译成中文

在这篇文章中，我们推导出一种最小化对数谱的均方误差的STSA估计器，并在增强嘈杂语音方面进行了研究。我们发现，这个估计器比[11]中导出的MMSE STSA估计器更优秀，因为它在不进一步影响语音本身的情况下，能够得到更低的残余噪声水平。事实上，这个新的估计器得到的增强语音质量与[11]中考虑到信号存在不确定性的MMSE STSA估计器非常相似。

帮我润色论文。In this paper, we propose a balancing training method to address problems in imbalanced data learning. To this end, we derive a new loss used in the balancing training phase that alleviates the influence of samples that cause an overfitted decision boundary. The proposed loss efficiently improves the performance of any type of imbalance learning methods. In experiments on multiple benchmark data sets, we demonstrate the validity of our method and reveal that the proposed loss outperforms the state-of-the-art cost-sensitive loss methods. Furthermore, since our loss is not restricted to a specific task, model, or training method, it can be easily used in combination with other recent resampling, meta-learning, and cost-sensitive learning methods for class-imbalance problems. Our code is made available at https://github.com/pseulki/IB-Loss.

在本文中，我们提出了一种平衡训练方法，以解决不平衡数据学习中的问题。为此，我们在平衡训练阶段推导出一种新的损失，以减少导致过度拟合决策边界的样本的影响。所提出的损失有效提高了任何类型的不平衡学习方法的性能。在多个基准数据集的实验中，我们证明了我们的方法的有效性，并发现所提出的损失优于最先进的成本敏感损失方法。此外，由于我们的损失不受特定任务、模型或训练方法的限制，它可以轻松与其他最近的重采样、元学习和成本敏感学习方法结合使用，以解决类不平衡问题。我们的代码可在 https://github.com/pseulki/IB-Loss 获得。