paper-with-me

홈 › Papers

No Free Lunch for Synthetic Images under Data Scarcity Conditions

2026-06-01 · Borja Arroyo Galende, Alejandro Almodóvar, Patricia A. Apellániz, Juan Parras, Silvia Uribe, Santiago Zazo arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.07640

Code (0)

등록된 구현이 없습니다.

Tasks

Synthetic Data Generation

Similar Papers 제목 키워드 기반

Free Lunch for Optimisation under the Universal Distribution

2016-08-16 · Tom Everitt, Tor Lattimore, Marcus Hutter

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

2026-02-12 · Yuhan Wei, Yuting He, Linshan Wu, Fuxiang Huang 외 arxiv

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 Learning

Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning

2024-12-18 · Brett Barkley, David Fridovich-Keil

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 Gym

The no-free-lunch theorems of supervised learning

2022-02-09 · Tom F. Sterkenburg, Peter D. Grünwald

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 TheoryPhilosophy

No-Free-Lunch Theories for Tensor-Network Machine Learning Models

2024-12-07 · Jing-Chuan Wu, Qi Ye, Dong-Ling Deng, Li-Wei Yu

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…