
On Codomain Separability and Label Inference from (Noisy) Loss Functions
Machine learning classifiers rely on loss functions for performance eval...
read it

Collaborative Causal Discovery with Atomic Interventions
We introduce a new Collaborative Causal Discovery problem, through which...
read it

Label Inference Attacks from Logloss Scores
Logloss (also known as crossentropy loss) metric is ubiquitously used ...
read it

Efficient Intervention Design for Causal Discovery with Latents
We consider recovering a causal graph in presence of latent variables, w...
read it

Restricted Isometry Property under High Correlations
Matrices satisfying the Restricted Isometry Property (RIP) play an impor...
read it

Deep Neural Network Approximation using Tensor Sketching
Deep neural networks are powerful learning models that achieve stateof...
read it

Verifying Properties of Binarized Deep Neural Networks
Understanding properties of deep neural networks is an important challen...
read it

Compressed Sparse Linear Regression
Highdimensional sparse linear regression is a basic problem in machine ...
read it

Private Incremental Regression
Data is continuously generated by modern data sources, and a recent chal...
read it

Simple BlackBox Adversarial Perturbations for Deep Networks
Deep neural networks are powerful and popular learning models that achie...
read it

Spectral Norm of Random Kernel Matrices with Applications to Privacy
Kernel methods are an extremely popular set of techniques used for many ...
read it
Shiva Prasad Kasiviswanathan
is this you? claim profile