198 citations · 481 across the 31 of their papers we have counts for
13 papers · 1 filter
Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model
Zinan Lin, Tadas Baltrusaitis, Wenyu Wang +1
Differentially private (DP) synthetic data enables the use of sensitive datasets while providing strong privacy guarantees. Recently, Private Evolution (PE) has emerged as a promis…
Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs
Enshu Liu, Junyi Zhu, Zinan Lin +6
The rapid advancement of large language models (LLMs) has led to architectures with billions to trillions of parameters, posing significant deployment challenges due to their subst…
Mixture-of-Linear-Experts for Long-term Time Series Forecasting
Ronghao Ni, Zinan Lin, Shuaiqi Wang +1
Long-term time series forecasting (LTSF) aims to predict future values of a time series given the past values. The current state-of-the-art (SOTA) on this problem is attained in so…
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Xinyu Tang, Richard Shin, Huseyin A. Inan +6
We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the priv…
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
Enshu Liu, Xuefei Ning, Zinan Lin +2
Diffusion probabilistic models (DPMs) are a new class of generative models that have achieved state-of-the-art generation quality in various domains. Despite the promise, one major…
Selective Pre-training for Private Fine-tuning
Da Yu, Sivakanth Gopi, Janardhan Kulkarni +5
Text prediction models, when used in applications like email clients or word processors, must protect user data privacy and adhere to model size constraints. These constraints are…
On the Privacy Properties of GAN-generated Samples
Zinan Lin, Vyas Sekar, Giulia Fanti
The privacy implications of generative adversarial networks (GANs) are a topic of great interest, leading to several recent algorithms for training GANs with privacy guarantees. By…
RareGAN: Generating Samples for Rare Classes
Zinan Lin, Hao Liang, Giulia Fanti +1
We study the problem of learning generative adversarial networks (GANs) for a rare class of an unlabeled dataset subject to a labeling budget. This problem is motivated from practi…
Pareto GAN: Extending the Representational Power of GANs to Heavy-Tailed Distributions
Todd Huster, Jeremy E. J. Cohen, Zinan Lin +5
Generative adversarial networks (GANs) are often billed as "universal distribution learners", but precisely what distributions they can represent and learn is still an open questio…
Why Spectral Normalization Stabilizes GANs: Analysis and Improvements
Zinan Lin, Vyas Sekar, Giulia Fanti
Spectral normalization (SN) is a widely-used technique for improving the stability and sample quality of Generative Adversarial Networks (GANs). However, there is currently limited…
Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions
Zinan Lin, Alankar Jain, Chen Wang +2
Limited data access is a longstanding barrier to data-driven research and development in the networked systems community. In this work, we explore if and how generative adversarial…
InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANs
Zinan Lin, Kiran Koshy Thekumparampil, Giulia Fanti +1
Disentangled generative models map a latent code vector to a target space, while enforcing that a subset of the learned latent codes are interpretable and associated with distinct…
PacGAN: The power of two samples in generative adversarial networks
Zinan Lin, Ashish Khetan, Giulia Fanti +1
Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable recent improvements i…