Applications
Preventing overfitting in deep learning using differential privacy
arXiv:2604.16334v1 Announce Type: new Abstract: The use of Deep Neural Network based systems in the real world is growing. They have achieved state-of-the-art performance on many image, speech and tex
arXiv:2604.16334v1 Announce Type: new Abstract: The use of Deep Neural Network based systems in the real world is growing. They have achieved state-of-the-art performance on many image, speech and text datasets. They have been shown to be powerful systems that are capable of learning detailed relationships and abstractions from the data. This is a double-edged sword which makes such systems vulnerable to learning the noise in the training set, thereby negatively impacting performance. This is also known as the problem of overfitting or poor generalization. In a practical setting, analysts typically have limited data to build models that must generalize to unseen data. In this work, we explore the use of a differential-privacy based approach to improve generalization in Deep Neural Networks.
Related
- Synthesizing real-world distributions from high-dimensional Gaussian Noise with Fully Connected Neural Network
- Robust Semi-Supervised Temporal Intrusion Detection for Adversarial Cloud Networks
- Local learning for stable backpropagation-free neural network training towards physical learning
- FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learning
Source: arXiv cs.LG | 2026-04-21