activity
20242026
collaborators

7 papers

cs.DS2026

Testing Distributions Against Bounded Distinguishers

Mark Bun, Rathin Desai, Renato Ferreira Pinto

Motivated by the challenge of testing distributions over high-dimensional or continuous domains, we study distribution testing with respect to bounded classes of distinguishers. A…

cs.CC2026

QMA Lower Bounds for Batch Verification via Approximate Degree

Mark Bun, Mandar Juvekar, Samuel King

We study batch verification in QMA query and communication complexity, where the goal is to understand how the resources needed to verify copies of a Boolean function depen…

cs.DS2026

Not All Learnable Distribution Classes are Privately Learnable

Mark Bun, Gautam Kamath, Argyris Mouzakis +1

We give an example of a class of distributions that is learnable up to constant error in total variation distance with a finite number of samples, but not learnable under $(\vareps…

cs.CR2026

Separating Oblivious and Adaptive Differential Privacy under Continual Observation

Mark Bun, Marco Gaboardi, Connor Wagaman

We resolve an open question of Jain, Raskhodnikova, Sivakumar, and Smith (ICML 2023) by exhibiting a problem separating differential privacy under continual observation in the obli…

cs.LG2026

Privately Learning Decision Lists and a Differentially Private Winnow

Mark Bun, William Fang

We give new differentially private algorithms for the classic problems of learning decision lists and large-margin halfspaces in the PAC and online models. In the PAC model, we giv…

cs.CR2025

Enforcing Demographic Coherence: A Harms Aware Framework for Reasoning about Private Data Release

Mark Bun, Marco Carmosino, Palak Jain +2

The technical literature about data privacy largely consists of two complementary approaches: formal definitions of conditions sufficient for privacy preservation and attacks that…