research
∙
05/26/2023
Differentially private low-dimensional representation of high-dimensional data
Differentially private synthetic data provide a powerful mechanism to en...
share
research
∙
02/11/2023
Algorithmically Effective Differentially Private Synthetic Data
We present a highly effective algorithmic approach for generating ε-diff...
research
∙
01/06/2023
Covariance loss, Szemeredi regularity, and differential privacy
We show how randomized rounding based on Grothendieck's identity can be ...
research
∙
05/31/2022
AVIDA: Alternating method for Visualizing and Integrating Data
High-dimensional multimodal data arises in many scientific fields. The i...
research
∙
04/20/2022
Private measures, random walks, and synthetic data
Differential privacy is a mathematical concept that provides an informat...
research
∙
02/15/2022
The Quarks of Attention
Attention plays a fundamental role in both natural and artificial intell...
research
∙
09/30/2021
Private sampling: a noiseless approach for generating differentially private synthetic data
In a world where artificial intelligence and data science become omnipre...
research
∙
09/03/2021
Privacy of synthetic data: a statistical framework
Privacy-preserving data analysis is emerging as a challenging problem wi...
research
∙
07/13/2021
Covariance's Loss is Privacy's Gain: Computationally Efficient, Private and Accurate Synthetic Data
The protection of private information is of vital importance in data-dri...
research
∙
02/19/2021
A theory of capacity and sparse neural encoding
Motivated by biological considerations, we study sparse neural maps from...
research
∙
01/20/2020
Memory capacity of neural networks with threshold and ReLU activations
Overwhelming theoretical and empirical evidence shows that mildly overpa...
research
∙
10/28/2019
Online Stochastic Gradient Descent with Arbitrary Initialization Solves Non-smooth, Non-convex Phase Retrieval
In recent literature, a general two step procedure has been formulated f...
research
∙
01/02/2019
The capacity of feedforward neural networks
A long standing open problem in the theory of neural networks is the dev...
research
∙
01/26/2018
Concentration of random graphs and application to community detection
Random matrix theory has played an important role in recent work on stat...
research
∙
04/04/2017
Polynomial Time and Sample Complexity for Non-Gaussian Component Analysis: Spectral Methods
The problem of Non-Gaussian Component Analysis (NGCA) is about finding a...
research
∙
05/31/2014
