activity
20172026
most citedDifferentially Private Identity and Closeness Testing of Discrete Distributions

10 citations · 12 across the 19 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2024

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…

cs.LG2024

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…