I am a third year PhD student 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.
- [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.
Estimating informativeness of samples with smooth unique information
ICLR 2021 [arXiv, code, bibTeX]
Improving generalization by controlling label-noise information in neural network weights
ICML 2020 [arXiv, code, bibTeX]
Fast structure learning with modular regularization
NeurIPS'19 [arXiv, code, bibTeX]
Efficient Covariance Estimation from Temporal Data
arXiv preprint [arXiv, code, bibTeX]
Mixhop: Higher-order graph convolution architectures via sparsified neighborhood mixing
ICML'19 [arXiv, code, bibTeX]
Multitask learning and benchmarking with clinical time series data
Nature, Scientific data 6 (1), 96 [arXiv, code, bibTeX]
Disentangled representations via synergy minimization
Allerton'17 [arXiv, bibTeX]