41 citations · 48 across the 5 of their papers we have counts for
7 papers · 1 filter
Stabilizing Bi-Level Hyperparameter Optimization using Moreau-Yosida Regularization
Sauptik Dhar, Unmesh Kurup, Mohak Shah
This research proposes to use the Moreau-Yosida envelope to stabilize the convergence behavior of bi-level Hyperparameter optimization solvers, and introduces the new algorithm cal…
Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey
Jiayi Liu, Samarth Tripathi, Unmesh Kurup +1
With the general trend of increasing Convolutional Neural Network (CNN) model sizes, model compression and acceleration techniques have become critical for the deployment of these…
Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter Tuning
Jiayi Liu, Samarth Tripathi, Unmesh Kurup +1
Tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming. In addition to the computational effort required,…
On-Device Machine Learning: An Algorithms and Learning Theory Perspective
Sauptik Dhar, Junyao Guo, Jiayi Liu +3
The predominant paradigm for using machine learning models on a device is to train a model in the cloud and perform inference using the trained model on the device. However, with i…
Improving Model Training by Periodic Sampling over Weight Distributions
Samarth Tripathi, Jiayi Liu, Unmesh Kurup +2
In this paper, we explore techniques centered around periodic sampling of model weights that provide convergence improvements on gradient update methods (vanilla \acs{SGD}, Momentu…
Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling
Jiayi Liu, Samarth Tripathi, Unmesh Kurup +1
Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning mod…