activity
20172022
most citedFast Low-Rank Matrix Estimation without the Condition Number

6 citations · 17 across the 10 of their papers we have counts for

collaborators

12 papers

cs.SD2021

A Methodology for Exploring Deep Convolutional Features in Relation to Hand-Crafted Features with an Application to Music Audio Modeling

Anna K. Yanchenko, Mohammadreza Soltani, Robert J. Ravier +2

Understanding the features learned by deep models is important from a model trust perspective, especially as deep systems are deployed in the real world. Most recent approaches for…

cs.LG2020

Task-Aware Neural Architecture Search

Cat P. Le, Mohammadreza Soltani, Robert Ravier +1

The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than t…

cs.LG20201 cited

Hyperparameter Optimization in Neural Networks via Structured Sparse Recovery

Minsu Cho, Mohammadreza Soltani, Chinmay Hegde

In this paper, we study two important problems in the automated design of neural networks -- Hyper-parameter Optimization (HPO), and Neural Architecture Search (NAS) -- through the…

cs.LG2020

GeoStat Representations of Time Series for Fast Classification

Robert J. Ravier, Mohammadreza Soltani, Miguel Simões +2

Recent advances in time series classification have largely focused on methods that either employ deep learning or utilize other machine learning models for feature extraction. Thou…

cs.LG2020

Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows

Chris Cannella, Mohammadreza Soltani, Vahid Tarokh

We introduce Projected Latent Markov Chain Monte Carlo (PL-MCMC), a technique for sampling from the high-dimensional conditional distributions learned by a normalizing flow. We pro…

cs.LG2019

Perception-Distortion Trade-off with Restricted Boltzmann Machines

Chris Cannella, Jie Ding, Mohammadreza Soltani +1

In this work, we introduce a new procedure for applying Restricted Boltzmann Machines (RBMs) to missing data inference tasks, based on linearization of the effective energy functio…