Search Results for author:
Found 16 papers, 7 papers with code
Membership Inference Attacks on Diffusion Models via Quantile Regression
Our proposed MI attack learns quantile regression models that predict (a quantile of) the distribution of reconstruction loss on examples not used in training.
Beta quantile regression for robust estimation of uncertainty in the presence of outliers
Outlier features can compromise the performance of deep learning regression problems such as style translation, image reconstruction, and deep anomaly detection, potentially leading to misleading conclusions.
Improved Differentially Private Regression via Gradient Boosting
We revisit the problem of differentially private squared error linear regression.
Private Synthetic Data for Multitask Learning and Marginal Queries
A key innovation in our algorithm is the ability to directly handle numerical features, in contrast to a number of related prior approaches which require numerical features to be first converted into {high cardinality} categorical features via {a binning strategy}.
Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detection
Here we address the problem of quantifying uncertainty in the images that are reconstructed by the VAE as the basis for principled outlier or lesion detection.
Differentially Private Query Release Through Adaptive Projection
We propose, implement, and evaluate a new algorithm for releasing answers to very large numbers of statistical queries like $k$-way marginals, subject to differential privacy.
Adversarial Robustness with Non-uniform Perturbations
Robustness of machine learning models is critical for security related applications, where real-world adversaries are uniquely focused on evading neural network based detectors.
Addressing Variance Shrinkage in Variational Autoencoders using Quantile Regression
Using estimated quantiles to compute mean and variance under the Gaussian assumption, we compute reconstruction probability as a principled approach to outlier or anomaly detection.
Robust Variational Autoencoder for Tabular Data with Beta Divergence
The source of outliers in training data include the data collection process itself (random noise) or a malicious attacker (data poisoning) who may target to degrade the performance of the machine learning model.
DropCluster: A structured dropout for convolutional networks
Dropout as a regularizer in deep neural networks has been less effective in convolutional layers than in fully connected layers.
Dynamic Local Regret for Non-convex Online Forecasting
We introduce a local regret for non-convex models in a dynamic environment.
ROMark: A Robust Watermarking System Using Adversarial Training
It protects the copyright of digital content by embedding imperceptible information into the data in the presence of an adversary.
Robust Variational Autoencoder
Machine learning methods often need a large amount of labeled training data.
Time-Smoothed Gradients for Online Forecasting
Here, we study different update rules in stochastic gradient descent (SGD) for online forecasting problems.
A Local Regret in Nonconvex Online Learning
We consider an online learning process to forecast a sequence of outcomes for nonconvex models.
Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured Data
In many applications where collecting data is expensive, for example neuroscience or medical imaging, the sample size is typically small compared to the feature dimension.
