10 citations · 12 across the 19 of their papers we have counts for
9 papers · 1 filter
High-Dimensional Robust Mean Estimation with Untrusted Batches
Maryam Aliakbarpour, Vladimir Braverman, Yuhan Liu +1
We study high-dimensional mean estimation in a collaborative setting where data is contributed by users in batches of size . In this environment, a learner seeks to recover…
Auditing Information Disclosure During LLM-Scale Gradient Descent Using Gradient Uniqueness
Sleem Abdelghafar, Maryam Aliakbarpour, Chris Jermaine
Disclosing information via the publication of a machine learning model poses significant privacy risks. However, auditing this disclosure across every datapoint during the training…
Support Basis: Fast Attention Beyond Bounded Entries
Maryam Aliakbarpour, Vladimir Braverman, Junze Yin +1
Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. However, the quadratic complexity of softmax attention remains a central bottlen…
Better Private Distribution Testing by Leveraging Unverified Auxiliary Data
Maryam Aliakbarpour, Arnav Burudgunte, Clément Cannone +1
We extend the framework of augmented distribution testing (Aliakbarpour, Indyk, Rubinfeld, and Silwal, NeurIPS 2024) to the differentially private setting. This captures scenarios…
Privacy in Metalearning and Multitask Learning: Modeling and Separations
Maryam Aliakbarpour, Konstantina Bairaktari, Adam Smith +2
Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop indiv…
Optimal Algorithms for Augmented Testing of Discrete Distributions
Maryam Aliakbarpour, Piotr Indyk, Ronitt Rubinfeld +1
We consider the problem of hypothesis testing for discrete distributions. In the standard model, where we have sample access to an underlying distribution , extensive research h…