# About me

I am a PhD candidate at University of Southern California advised by Prof. Aram Galstyan and Prof. Greg Ver Steeg. I do both applied and theoretical research on some aspects of deep learning, often taking an information-theoretic perspective. My main research directions are (a) studying information stored in neural network weights or activations and its connections to generalization, memorization, stability and learning dynamics; and (b) representation learning with the goal of enriching the learned representation with useful properties, such as minimality, disentanglement, modularity, reduced synergy, etc. More broadly, I am interested in designing novel representation learning approaches, unsupervised/self-supervised learning, studying the generalization phenomenon of deep neural networks, and in estimation/approximation of information-theoretic quantities or their alternatives.

## News

**[Sept. 28, 2021]**Our work “Information-theoretic generalization bounds for black-box learning algorithms” was accepted to NeurIPS 2021.**[May 17, 2021]**Started a summer internship at AWS Custom Labels team. Will be working with Alessandro Achille and Avinash Ravichandran.**[Jan. 12, 2021]**Our work “Estimating informativeness of samples with Smooth Unique Information” got accepted to ICLR 2021.**[Oct. 20, 2020]**Received a free NeurIPS 2020 registration by making it to the list of the top 10% of high-scoring reviewers.**[June 3, 2020]**Our work “Improving generalization by controlling label-noise information in neural network weights” got accepted to ICML 2020.**[May 18, 2020]**Starting a summer internship at AWS Custom Labels team. Going to work with Alessandro Achille, Avinash Ravichandran, and Orchid Majumder!**[Jan. 3, 2020]**I will be TA-ing CSCI 270: “introduction to algorithms and theory of computing” taught by Prof. Shahriar Shamsian this spring.**[Oct. 1, 2019]**Our work titled “Reducing overfitting by minimizing label information in weights” got accepted to NeurIPS’19 information theory and machine learning workshop.**[Sept. 3, 2019]**Our paper “Fast structure learning with modular regularization” got accepted to NeurIPS’19 as a spotlight presentation.**[Aug. 15, 2019]**I will be the teaching assistant of CSCI 670: “advanced analysis of algorithms” taught by Prof. Shang-Hua Teng this fall.

## Publications and preprints

*Hrayr Harutyunyan*, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan

**Failure Modes of Domain Generalization Algorithms**

arXiv preprint [arXiv, code 1 2, bibTeX]

*Hrayr Harutyunyan*, Maxim Raginsky, Greg Ver Steeg, Aram Galstyan

**Information-theoretic generalization bounds for black-box learning algorithms**

NeurIPS 2021 [arXiv, code, bibTeX]

*Hrayr Harutyunyan*, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto

**Estimating informativeness of samples with smooth unique information**

ICLR 2021 [arXiv, code, bibTeX]

*Hrayr Harutyunyan*, Kyle Reing, Greg Ver Steeg, Aram Galstyan

**Improving generalization by controlling label-noise information in neural network weights**

ICML 2020 [arXiv, code, bibTeX]

*Hrayr Harutyunyan*, Daniel Moyer, Aram Galstyan

**Fast structure learning with modular regularization**

NeurIPS'19 [arXiv, code, bibTeX]

*Hrayr Harutyunyan*, Daniel Moyer, Hrant Khachatrian, Greg Ver Steeg, Aram Galstyan

**Efficient Covariance Estimation from Temporal Data**

arXiv preprint [arXiv, code, bibTeX]

*Hrayr Harutyunyan*, Nazanin Alipourfard, Kristina Lerman, Greg Ver Steeg, Aram Galstyan

**Mixhop: Higher-order graph convolution architectures via sparsified neighborhood mixing**

ICML'19 [arXiv, code, bibTeX]

*Hrayr Harutyunyan*, Hrant Khachatrian, David Kale, Greg Ver Steeg, Aram Galstyan

**Multitask learning and benchmarking with clinical time series data**

Nature, Scientific data 6 (1), 96 [arXiv, code, bibTeX]

*Hrayr Harutyunyan*, Aram Galstyan

**Disentangled representations via synergy minimization**

Allerton'17 [arXiv, bibTeX]