activity
20172020
most cited2-Wasserstein Approximation via Restricted Convex Potentials with Application to Improved Training for GANs

21 citations · 30 across the 5 of their papers we have counts for

collaborators

6 papers

stat.ML2020

Persistent Reductions in Regularized Loss Minimization for Variable Selection

Amin Jalali

In the context of regularized loss minimization with polyhedral gauges, we show that for a broad class of loss functions (possibly non-smooth and non-convex) and under a simple geo…

stat.ML20191 cited

New Computational and Statistical Aspects of Regularized Regression with Application to Rare Feature Selection and Aggregation

Amin Jalali, Adel Javanmard, Maryam Fazel

Prior knowledge on properties of a target model often come as discrete or combinatorial descriptions. This work provides a unified computational framework for defining norms that p…

eess.SP2019

A New Algorithm for Improved Blind Detection of Polar Coded PDCCH in 5G New Radio

Amin Jalali, Zhi Ding

In recent release of the new cellular standard known as 5G New Radio (5G-NR), the physical downlink control channel (PDCCH) has adopted polar codes for error protection. Similar to…

math.OC201921 cited

2-Wasserstein Approximation via Restricted Convex Potentials with Application to Improved Training for GANs

Amirhossein Taghvaei, Amin Jalali

We provide a framework to approximate the 2-Wasserstein distance and the optimal transport map, amenable to efficient training as well as statistical and geometric analysis. With t…

stat.ML2018

Missing Data in Sparse Transition Matrix Estimation for Sub-Gaussian Vector Autoregressive Processes

Amin Jalali, Rebecca Willett

High-dimensional time series data exist in numerous areas such as finance, genomics, healthcare, and neuroscience. An unavoidable aspect of all such datasets is missing data, and d…

stat.ML20178 cited

Subspace Clustering with Missing and Corrupted Data

Zachary Charles, Amin Jalali, Rebecca Willett

Given full or partial information about a collection of points that lie close to a union of several subspaces, subspace clustering refers to the process of clustering the points ac…