Fast john ellipsoid computation with differential privacy optimization

J Gu, X Li, Y Liang, Z Shi, Z Song, J Yu - arxiv preprint arxiv:2408.06395, 2024 - arxiv.org
Determining the John ellipsoid-the largest volume ellipsoid contained within a convex
polytope-is a fundamental problem with applications in machine learning, optimization, and …

Iterative sketching for secure coded regression

N Charalambides, H Mahdavifar… - IEEE Journal on …, 2024 - ieeexplore.ieee.org
Linear regression is a fundamental and primitive problem in supervised machine learning,
with applications ranging from epidemiology to finance. In this work, we propose methods for …

Distributed Local Sketching for£ 2 Embeddings

N Charalambides, A Mazumdar - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
In this work, we show that if local datasets in a distributed network are appropriately
compressed and then aggregated, it can result in a compressed version of the union of the …

Distributed Hybrid Sketching for -Embeddings

N Charalambides, A Mazumdar - arxiv preprint arxiv:2412.20301, 2024 - arxiv.org
Linear algebraic operations are ubiquitous in engineering applications, and arise often in a
variety of fields including statistical signal processing and machine learning. With …

Coding Theory and Randomized Sketching for Distributed Optimization

N Charalambides - 2023 - search.proquest.com
With the advent of massive datasets, distributed techniques for processing information and
carrying out computations are expected to enable exceptional possibilities for engineering …