Related papers: Characterizing the Training Dynamics of Private Fi…

Collaborative machine learning techniques such as federated learning (FL) enable the training of models on effectively larger datasets without data transfer. Recent initiatives have demonstrated that segmentation models trained with FL can…

Large language models are prone to hallucinating factually incorrect statements. A key source of these errors is exposure to new factual information through supervised fine-tuning (SFT), which can increase hallucinations w.r.t. knowledge…

Real-world model deployments demand strong performance on narrow domains where data is often scarce. Typically, practitioners finetune models to specialize them, but this risks overfitting to the domain and forgetting general knowledge. We…

Differentially private (DP) transfer learning, i.e., fine-tuning a pretrained model on private data, is the current state-of-the-art approach for training large models under privacy constraints. We focus on two key hyperparameters in this…

Classifiers that are linear in their parameters, and trained by optimizing a convex loss function, have predictable behavior with respect to changes in the training data, initial conditions, and optimization. Such desirable properties are…

Federated learning (FL) enables collaborative model training across distributed clients without sharing raw data, making it a promising approach for privacy-preserving machine learning. However, ensuring differential privacy (DP) in FL…

This study addresses the issues of privacy protection and efficiency in instruction fine-tuning of large-scale language models by proposing a parameter-efficient method that integrates differential privacy noise allocation with gradient…

The powerful cooperation of federated learning (FL) and differential privacy~(DP) provides a promising paradigm for the large-scale private clients. However, existing analyses in FL-DP mostly rely on the composition theorem and cannot…

Differentially private stochastic gradient descent (DP-SGD) is broadly considered to be the gold standard for training and fine-tuning neural networks under differential privacy (DP). With the increasing availability of high-quality…

We introduce DP-FinDiff, a differentially private diffusion framework for synthesizing mixed-type tabular data. DP-FinDiff employs embedding-based representations for categorical features, reducing encoding overhead and scaling to…

Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from standard training, whereas understanding the geometric…

In spite that Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively, recent studies have pointed out that the naive FL is susceptible to gradient…

User-level differential privacy (DP) provides certifiable privacy guarantees to the information that is specific to any user's data in federated learning. Existing methods that ensure user-level DP come at the cost of severe accuracy…

Developing a differentially private deep learning algorithm is challenging, due to the difficulty in analyzing the sensitivity of objective functions that are typically used to train deep neural networks. Many existing methods resort to the…

Federated learning (FL), a novel branch of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, it is still possible to access the model updates (gradient…

Personalized federated learning (PFL) has garnered significant attention for its ability to address heterogeneous client data distributions while preserving data privacy. However, when local client data is limited, deep learning models…

Foundation models have revolutionized artificial intelligence by providing robust, versatile architectures pre-trained on large-scale datasets. However, adapting these massive models to specific downstream tasks requires fine-tuning, which…

Fine-tuning is known to improve NLP models by adapting an initial model trained on more plentiful but less domain-salient examples to data in a target domain. Such domain adaptation is typically done using one stage of fine-tuning. We…

Fine-tuning large pre-trained foundation models (FMs) on distributed edge devices presents considerable computational and privacy challenges. Federated fine-tuning (FedFT) mitigates some privacy issues by facilitating collaborative model…

In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in…