About Me
I am a fourth-year PhD student at Max-Planck-Institute for Intelligent Systems and University of Tübingen in Germany. I am an information-theorist and computer scientist, working on a variety of topics in machine learning. I have done my masters at Sharif University of Technology in Iran in 2019.
During my masters, I done a research internship at National Yang Ming Chiao Tung University in Taiwan.
Besides my academic life, I am interested in Persian poetry, reading and writing fictional stories, and talking philosophy. If you want to chat, just drop me an email or find me on Twitter. You can find me on GitHub and LinkedIn, and Google Scholar too.
Machine Learning Projects
Sample Efficient Learning of Predictors that Complement Humans

Sample Efficient Learning of Predictors that Complement Humans

In here, we provide first theoretical results on joint learning of classifier and rejector, we design an active learning algorithm to do so, and we further introduce a set of surrogate losses to make the learn-to-defer training possible for neural networks.
Hermite Polynomial Features for Private Data Generation

Hermite Polynomial Features for Private Data Generation

In this paper, we designed an alternative to random features to generate more efficient representations of a dataset that further could be privacy-preserving with maintaining the quality of the instances.
Information Theory Projects
Compressibility Measures for Affinely Singular Random Vectors

Compressibility Measures for Affinely Singular Random Vectors

In this paper, we define a set of singular distributions that naturally arise in autoregressive processes. Then, we obtain R'enyi information dimension for processes with such probability distribution. We further, find an extension to differential entropy for such class of probability measures. Then, we find information-theoretic and compressed-sensing reconstruction errors for compression of samples of such processes.
On the Compressibility of Affinely Singular Random Vectors

On the Compressibility of Affinely Singular Random Vectors

In this paper, I find a probabilistic extension to sparsity that can lead to similar guarantees in reconstruction error in compressed sensing problems. This is done by finding R'enyi Information Dimension for probability measures with singularity.