No Free Lunch for Synthetic Images under Data Scarcity Conditions
This study investigates the trade-offs between fidelity, privacy, and utility in synthetic data generation under conditions of data scarcity and privacy sensitivity. We propose an evaluation framework that jointly assesses these three dimensions and apply it to three widely used generative models, VAE, GAN, and DDPM. The evaluation spans three image datasets, MNIST, OCTMNIST, and OrganAMNIST, encompassing both general-purpose and medical imaging domains. Notable differences arise between the three models in their behaviour when differential privacy mechanisms are introduced during training. GAN and DDPM demonstrate greater robustness, maintaining higher fidelity and downstream utility across a range of noise levels, while VAE degrades more rapidly as privacy constraints increase. This study highlights the importance of a multidimensional evaluation of deep generative models, also noting that their behaviour significantly differs when privacy techniques are applied.
Code (0)
등록된 구현이 없습니다.
Tasks
Synthetic Data GenerationSimilar Papers 제목 키워드 기반
Free Lunch for Optimisation under the Universal Distribution
Function optimisation is a major challenge in computer science. The No Free Lunch theorems state that if all functions with the same histogram are assumed to be equally probable then no algorithm outperforms any other in…
Free Lunch in Medical Image Foundation Model Pre-training via Randomized Synthesis and Disentanglement
Medical image foundation models (MIFMs) have demonstrated remarkable potential for a wide range of clinical tasks, yet their development is constrained by the scarcity, heterogeneity, and high cost of large-scale annotat…
Representation LearningStealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning
Dyna-style off-policy model-based reinforcement learning (DMBRL) algorithms are a family of techniques for generating synthetic state transition data and thereby enhancing the sample efficiency of off-policy RL algorithm…
Model-based Reinforcement LearningOpenAI GymThe no-free-lunch theorems of supervised learning
The no-free-lunch theorems promote a skeptical conclusion that all possible machine learning algorithms equally lack justification. But how could this leave room for a learning theory, that shows that some algorithms are…
Inductive BiasLearning TheoryPhilosophyNo-Free-Lunch Theories for Tensor-Network Machine Learning Models
Tensor network machine learning models have shown remarkable versatility in tackling complex data-driven tasks, ranging from quantum many-body problems to classical pattern recognitions. Despite their promising performan…