Search Results for author:
Found 13 papers, 0 papers with code
Online Differentially Private Synthetic Data Generation
We present a polynomial-time algorithm for online differentially private synthetic data generation.
An Algorithm for Streaming Differentially Private Data
Much of the research in differential privacy has focused on offline applications with the assumption that all data is available at once.
Differentially Private Low-dimensional Synthetic Data from High-dimensional Datasets
Differentially private synthetic data provide a powerful mechanism to enable data analysis while protecting sensitive information about individuals.
AVIDA: Alternating method for Visualizing and Integrating Data
In general applications, other methods can be used for the alignment and dimension reduction modules.
The Quarks of Attention
The gating mechanisms correspond to multiplicative extensions of the standard model and are used across all current attention-based deep learning architectures.
A theory of capacity and sparse neural encoding
Motivated by biological considerations, we study sparse neural maps from an input layer to a target layer with sparse activity, and specifically the problem of storing $K$ input-target associations $(x, y)$, or memories, when the target vectors $y$ are sparse.
Memory capacity of neural networks with threshold and ReLU activations
Overwhelming theoretical and empirical evidence shows that mildly overparametrized neural networks -- those with more connections than the size of the training data -- are often able to memorize the training data with $100\%$ accuracy.
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 for solving the problem of phase retrieval.
The capacity of feedforward neural networks
Here we define the capacity of an architecture by the binary logarithm of the number of functions it can compute, as the synaptic weights are varied.
On Neuronal Capacity
We define the capacity of a learning machine to be the logarithm of the number (or volume) of the functions it can implement.
Phase Retrieval via Randomized Kaczmarz: Theoretical Guarantees
We consider the problem of phase retrieval, i. e. that of solving systems of quadratic equations.
Polynomial Time and Sample Complexity for Non-Gaussian Component Analysis: Spectral Methods
The problem of Non-Gaussian Component Analysis (NGCA) is about finding a maximal low-dimensional subspace $E$ in $\mathbb{R}^n$ so that data points projected onto $E$ follow a non-gaussian distribution.
Optimization via Low-rank Approximation for Community Detection in Networks
Community detection is one of the fundamental problems of network analysis, for which a number of methods have been proposed.
