Search Results for author:
Found 18 papers, 2 papers with code
Differentially Private Conditional Independence Testing
We provide theoretical guarantees on the performance of our tests and validate them empirically.
Debiasing Conditional Stochastic Optimization
In this paper, we study the conditional stochastic optimization (CSO) problem which covers a variety of applications including portfolio selection, reinforcement learning, robust learning, causal inference, etc.
Interventional and Counterfactual Inference with Diffusion Models
We consider the problem of answering observational, interventional, and counterfactual queries in a causally sufficient setting where only observational data and the causal graph are available.
Thompson Sampling with Diffusion Generative Prior
In this work, we initiate the idea of using denoising diffusion models to learn priors for online decision making problems.
Sequential Kernelized Independence Testing
Independence testing is a classical statistical problem that has been extensively studied in the batch setting when one fixes the sample size before collecting data.
Uplifting Bandits
We introduce a multi-armed bandit model where the reward is a sum of multiple random variables, and each action only alters the distributions of some of them.
Reconstructing Test Labels from Noisy Loss Functions
Machine learning classifiers rely on loss functions for performance evaluation, often on a private (hidden) dataset.
Collaborative Causal Discovery with Atomic Interventions
We introduce a new Collaborative Causal Discovery problem, through which we model a common scenario in which we have multiple independent entities each with their own causal graph, and the goal is to simultaneously learn all these causal graphs.
Label Inference Attacks from Log-loss Scores
Log-loss (also known as cross-entropy loss) metric is ubiquitously used across machine learning applications to assess the performance of classification algorithms.
Efficient Intervention Design for Causal Discovery with Latents
We consider recovering a causal graph in presence of latent variables, where we seek to minimize the cost of interventions used in the recovery process.
Restricted Isometry Property under High Correlations
Matrices satisfying the Restricted Isometry Property (RIP) play an important role in the areas of compressed sensing and statistical learning.
Deep Neural Network Approximation using Tensor Sketching
Deep neural networks are powerful learning models that achieve state-of-the-art performance on many computer vision, speech, and language processing tasks.
Verifying Properties of Binarized Deep Neural Networks
To the best of our knowledge, this is the first work on verifying properties of deep neural networks using an exact Boolean encoding of the network.
Restricted Eigenvalue from Stable Rank with Applications to Sparse Linear Regression
This construction allows incorporating a fixed matrix that has an easily {\em verifiable} condition into the design process, and allows for generation of {\em compressed} design matrices that have a lower storage requirement than a standard design matrix.
Private Incremental Regression
Our first contribution is a generic transformation of private batch ERM mechanisms into private incremental ERM mechanisms, based on a simple idea of invoking the private batch ERM procedure at some regular time intervals.
Simple Black-Box Adversarial Perturbations for Deep Networks
In this work, we focus on deep convolutional neural networks and demonstrate that adversaries can easily craft adversarial examples even without any internal knowledge of the target network.
Spectral Norm of Random Kernel Matrices with Applications to Privacy
In this paper, we initiate the study of non-asymptotic spectral theory of random kernel matrices.
What Can We Learn Privately?
Therefore, almost anything learnable is learnable privately: specifically, if a concept class is learnable by a (non-private) algorithm with polynomial sample complexity and output size, then it can be learned privately using a polynomial number of samples.
