We study fine-grained error bounds for differentially private algorithms for counting under
continual observation. Our main insight is that the matrix mechanism when using lower …

Large language models (LLMs), especially those based on the Transformer architecture,
have had a profound impact on various aspects of daily life, such as natural language …

Large language models (LLMs) have demonstrated exceptional performance across a wide
range of tasks. These models, powered by advanced deep learning techniques, have …

Large language models (LLMs) have shown their power in different areas. Attention
computation, as an important subroutine of LLMs, has also attracted interests in theory …

Privacy is a central challenge for systems that learn from sensitive data sets, especially
when a system's outputs must be continuously updated to reflect changing data. We …

We study the problem of maintaining a differentially private decaying sum under continual
observation. We give a unifying framework and an efficient algorithm for this problem for any …

We study fine-grained error bounds for differentially private algorithms for counting under
continual observation. Our main insight is that the matrix mechanism when using lower …

We develop a framework for efficiently transforming certain approximation algorithms into
differentially-private variants, in a black-box manner. Specifically, our results focus on …

Differentially private weighted prefix sum under continual observation is a crucial component
in the production-level deployment of private next-word prediction for Gboard, which …

Privately counting distinct elements in a stream is a fundamental data analysis problem with
many applications in machine learning. In the turnstile model, Jain et al.[NeurIPS2023] …