Academics

Research Interests

  • Machine learning

  • High dimensional statistics

  • Optimization

  • Graphical models and message passing algorithms

Publications

The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization

Daniel LeJeune, Hamid Javadi, and Richard G. Baraniuk

Advances in Neural Information Processing Systems Foundation (NeurIPS), 2021


Minipatch Learning as Implicit Ridge-Like Regularization

Tianyi Yao, Daniel LeJeune, Hamid Javadi, Richard G. Baraniuk, ans Genevera I. Allen

IEEE International Conference on Big Data and Smart Computing (BigComp), 2021


The Implicit Regularization of Ordinary Least Squares Ensembles

Daniel LeJeune, Hamid Javadi, and Richard G. Baraniuk

AISTATS, 2020


Non-negative Matrix Factorization via Archetypal Analysis (Website)

Hamid Javadi and Andrea Montanari

Journal of the American Statistical Association (2019), DOI: 10.1080/01621459.2019.1594832


An Instability in Variational Inference for Topic Models

Behrooz Ghorbani, Hamid Javadi, and Andrea Montanari

International Conference on Machine Learning (ICML), 2019.


False Discovery Rate via Debiased Lasso

Adel Javanmard and Hamid Javadi

Electronic Journal of Statistics 13.1 (2019): 1212-1253.


A Statistical Model for Motifs Detection

Hamid Javadi and Andrea Montanari

IEEE Transaction on Information Theory, vol. 64, no. 12, pp 7594-7612, Dec 2018.


Porcupine Neural Networks: Approximating Neural Network Landscapes

Soheil Feizi, Hamid Javadi, Jesse Zhang, and David Tse

Advances in Neural Information Processing Systems Foundation (NeurIPS), 2018


Tensor Biclustering

Soheil Feizi, Hamid Javadi, and David Tse

Advances in Neural Information Processing Systems Foundation (NeurIPS), 2017

Selected Courses

Inference, estimation, and information processing; Convex optimization I, II; Machine learning; Statistical learning theory;

Theory of statistics; Stochastic processes on graphs; Mining massive datasets; Information theory and statistics;

Advaced topics in convex optimization; Spectral graph theory; Randomized algorithms; Reinforcement learning;

Modern Applied Statistics; Network information theory; Stochastic control.

Selected Projects

ADMM Preconditioning via Diagonal Scaling (with Reza Takapoui) [Poster]

EE 364B: Convex optimization II, Instructor: Prof. Stephen Boyd


R-package for Confidence Intervals for High Dimensional Regression (with Adel Javanmard, Andrea Montanari and Sven Schmit)

sslasso: (zip)(tar.gz)


Douglas-Rachford Splitting for Cardinality Constrained Quadratic Programming (with Reza Takapoui and Enzo Busseti)

MATH 301: Advanced Topics in Convex Optimization, Instructor: Prof. Emmanuel Candes


An Efficient Algorithm for Low-Rank Kernel Regression (with Yash Deshpande)

CS 229T: Statistical Learning Theory, Instructor: Prof. Percy Liang