18 citations · 69 across the 20 of their papers we have counts for
11 papers · 1 filter
On The Energy Statistics of Feature Maps in Pruning of Neural Networks with Skip-Connections
Mohammadreza Soltani, Suya Wu, Yuerong Li +2
We propose a new structured pruning framework for compressing Deep Neural Networks (DNNs) with skip connections, based on measuring the statistical dependency of hidden layers and…
Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions
Juncheng Dong, Simiao Ren, Yang Deng +5
Numerous physical systems are described by ordinary or partial differential equations whose solutions are given by holomorphic or meromorphic functions in the complex domain. In ma…
Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
Cat P. Le, Juncheng Dong, Mohammadreza Soltani +1
We propose an asymmetric affinity score for representing the complexity of utilizing the knowledge of one task for learning another one. Our method is based on the maximum bipartit…
Fisher Task Distance and Its Application in Neural Architecture Search
Cat P. Le, Mohammadreza Soltani, Juncheng Dong +1
We formulate an asymmetric (or non-commutative) distance between tasks based on Fisher Information Matrices, called Fisher task distance. This distance represents the complexity of…
Improved Automated Machine Learning from Transfer Learning
Cat P. Le, Mohammadreza Soltani, Robert Ravier +1
In this paper, we propose a neural architecture search framework based on a similarity measure between some baseline tasks and a target task. We first define the notion of the task…
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…
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…
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…
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…
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…
One-Shot Neural Architecture Search via Compressive Sensing
Minsu Cho, Mohammadreza Soltani, Chinmay Hegde
Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time…