Search Results for author:
Found 10 papers, 6 papers with code
Strong convexity-guided hyper-parameter optimization for flatter losses
We propose a novel white-box approach to hyper-parameter optimization.
SMOOTHIE: A Theory of Hyper-parameter Optimization for Software Analytics
We hence conclude that this theory (that hyper-parameter optimization is best viewed as a ``smoothing'' function for the decision landscape), is both theoretically interesting and practically very useful.
How to Find Actionable Static Analysis Warnings: A Case Study with FindBugs
Automatically generated static code warnings suffer from a large number of false alarms.
An Expert System for Redesigning Software for Cloud Applications
When services are divided into many independent components, they are easier to update.
Old but Gold: Reconsidering the value of feedforward learners for software analytics
We test the hypothesis laid by Galke and Scherp [18], that feedforward networks suffice for many analytics tasks (which we call, the "Old but Gold" hypothesis) for these two tasks.
Text Mining to Identify and Extract Novel Disease Treatments From Unstructured Datasets
Results: We found 30. 4% of our proposed pairs in the ROBOKOP database.
Parsimonious Computing: A Minority Training Regime for Effective Prediction in Large Microarray Expression Data Sets
We leveraged the functional property of Mean Square Error, which is Lipschitz continuous to compute learning rate in shallow neural networks.
Simpler Hyperparameter Optimization for Software Analytics: Why, How, When?
How can we make software analytics simpler and faster?
Evolution of Novel Activation Functions in Neural Network Training with Applications to Classification of Exoplanets
We present analytical exploration of novel activation functions as consequence of integration of several ideas leading to implementation and subsequent use in habitability classification of exoplanets.
LipschitzLR: Using theoretically computed adaptive learning rates for fast convergence
In this paper, we propose a novel method to compute the learning rate for training deep neural networks with stochastic gradient descent.
