Andre Manoel

Efficient Per-Example Gradient Computations in Convolutional Neural Networks

2019 · arXiv (Cornell University)

Deep learning frameworks leverage GPUs to perform massively-parallel computations over batches of many training examples efficiently. However, for certain tasks, one may be interested in performing per-example computations, for instance using per-example gradients to evaluate …

Federated Survival Analysis with Discrete-Time Cox Models

2020 · arXiv (Cornell University)

Building machine learning models from decentralized datasets located in different centers with federated learning (FL) is a promising approach to circumvent local data scarcity while preserving privacy. However, the prominent Cox proportional hazards (PH) model, …

Differentially Private Fine-tuning of Language Models

2024 · Journal of Privacy and Confidentiality

We give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models, which achieve the state-of-the-art privacy versus utility tradeoffs on many standard NLP tasks. We propose a meta-framework for this …

Controllable Synthetic Clinical Note Generation with Privacy Guarantees

2024 · arXiv (Cornell University)

In the field of machine learning, domain-specific annotated data is an invaluable resource for training effective models. However, in the medical domain, this data often includes Personal Health Information (PHI), raising significant privacy concerns. The …