Search Results for author:
Found 29 papers, 10 papers with code
Pre-Pruning and Gradient-Dropping Improve Differentially Private Image Classification
To tackle this challenge, we take advantage of the fact that neural networks are overparameterized, which allows us to improve neural network training with differential privacy.
Differentially Private Latent Diffusion Models
In this paper, we further improve the current state of DMs with DP by adopting the Latent Diffusion Models (LDMs).
Differential Privacy Meets Neural Network Pruning
We study the interplay between neural network pruning and differential privacy, through the two modes of parameter updates.
Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation
Maximum mean discrepancy (MMD) is a particularly useful distance metric for differentially private data generation: when used with finite-dimensional features it allows us to summarize and privatize the data distribution once, which we can repeatedly use during generator training without further privacy loss.
Pre-trained Perceptual Features Improve Differentially Private Image Generation
Training even moderately-sized generative models with differentially-private stochastic gradient descent (DP-SGD) is difficult: the required level of noise for reasonable levels of privacy is simply too large.
Differentially private stochastic expectation propagation (DP-SEP)
We provide a theoretical analysis of the privacy-accuracy trade-off in the posterior estimates under our method, called differentially private stochastic expectation propagation (DP-SEP).
Hermite Polynomial Features for Private Data Generation
Hence, a relatively low order of Hermite polynomial features can more accurately approximate the mean embedding of the data distribution compared to a significantly higher number of random features.
Dirichlet Pruning for Neural Network Compression
We introduce Dirichlet pruning, a novel post-processing technique to transform a large neural network model into a compressed one.
Bayesian Importance of Features (BIF)
We introduce a simple and intuitive framework that provides quantitative explanations of statistical models through the probabilistic assessment of input feature importance.
DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation
We propose a differentially private data generation paradigm using random feature representations of kernel mean embeddings when comparing the distribution of true data with that of synthetic data.
DP-MAC: The Differentially Private Method of Auxiliary Coordinates for Deep Learning
Developing a differentially private deep learning algorithm is challenging, due to the difficulty in analyzing the sensitivity of objective functions that are typically used to train deep neural networks.
ABCDP: Approximate Bayesian Computation with Differential Privacy
SVT incurs the privacy cost only when a condition (whether a quantity of interest is above/below a threshold) is met.
Neuron ranking -- an informed way to condense convolutional neural networks architecture
Convolutional neural networks (CNNs) in recent years have made a dramatic impact in science, technology and industry, yet the theoretical mechanism of CNN architecture design remains surprisingly vague.
Interpretable and Differentially Private Predictions
Interpretable predictions, where it is clear why a machine learning model has made a particular decision, can compromise privacy by revealing the characteristics of individual data points.
Privacy-Preserving Causal Inference via Inverse Probability Weighting
The use of inverse probability weighting (IPW) methods to estimate the causal effect of treatments from observational studies is widespread in econometrics, medicine and social sciences.
Radial and Directional Posteriors for Bayesian Neural Networks
We propose a new variational family for Bayesian neural networks.
A Differentially Private Kernel Two-Sample Test
As a result, a simple chi-squared test is obtained, where a test statistic depends on a mean and covariance of empirical differences between the samples, which we perturb for a privacy guarantee.
Variational Bayes In Private Settings (VIPS)
Many applications of Bayesian data analysis involve sensitive information, motivating methods which ensure that privacy is protected.
Private Topic Modeling
We develop a privatised stochastic variational inference method for Latent Dirichlet Allocation (LDA).
A note on privacy preserving iteratively reweighted least squares
In particular, IRLS for L1 minimisation under the linear model provides a closed-form solution in each step, which is a simple multiplication between the inverse of the weighted second moment matrix and the weighted first moment vector.
DP-EM: Differentially Private Expectation Maximization
The iterative nature of the expectation maximization (EM) algorithm presents a challenge for privacy-preserving estimation, as each iteration increases the amount of noise needed.
Unlocking neural population non-stationarities using hierarchical dynamics models
Neural population activity often exhibits rich variability.
K2-ABC: Approximate Bayesian Computation with Kernel Embeddings
Complicated generative models often result in a situation where computing the likelihood of observed data is intractable, while simulating from the conditional density given a parameter value is relatively easy.
Sparse Bayesian structure learning with “dependent relevance determination” priors
Classical sparse regression methods, such as the lasso and automatic relevance determination (ARD), model parameters as independent a priori, and therefore do not exploit such dependencies.
Bayesian Manifold Learning: The Locally Linear Latent Variable Model (LL-LVM)
We introduce the Locally Linear Latent Variable Model (LL-LVM), a probabilistic model for non-linear manifold discovery that describes a joint distribution over observations, their manifold coordinates and locally linear maps conditioned on a set of neighbourhood relationships.
Hierarchical models for neural population dynamics in the presence of non-stationarity
Here, we introduce a hierarchical statistical model of neural population activity which models both neural population dynamics as well as inter-trial modulations in firing rates.
Bayesian inference for low rank spatiotemporal neural receptive fields
In typical experiments with naturalistic or flickering spatiotemporal stimuli, RFs are very high-dimensional, due to the large number of coefficients needed to specify an integration profile across time and space.
Bayesian active learning with localized priors for fast receptive field characterization
Active learning can substantially improve the yield of neurophysiology experiments by adaptively selecting stimuli to probe a neuron's receptive field (RF) in real time.
Active learning of neural response functions with Gaussian processes
With simulated experiments, we show that optimal design substantially reduces the amount of data required to estimate this nonlinear combination rule.
