Dominic Kafka

Orcid: 0000-0001-9023-5679

According to our database1, Dominic Kafka authored at least 8 papers between 2019 and 2023.

Collaborative distances:
  • Dijkstra number2 of six.
  • Erdős number3 of six.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2023
Gradient-only surrogate to resolve learning rates for robust and consistent training of deep neural networks.
Appl. Intell., June, 2023

2021
Resolving learning rates adaptively by locating stochastic non-negative associated gradient projection points using line searches.
J. Glob. Optim., 2021

An empirical study into finding optima in stochastic optimization of neural networks.
Inf. Sci., 2021

GOALS: Gradient-Only Approximations for Line Searches Towards Robust and Consistent Training of Deep Neural Networks.
CoRR, 2021

2020
Gradient-only line searches to automatically determine learning rates for a variety of stochastic training algorithms.
CoRR, 2020

Investigating the interaction between gradient-only line searches and different activation functions.
CoRR, 2020

2019
Gradient-only line searches: An Alternative to Probabilistic Line Searches.
CoRR, 2019

Visual interpretation of the robustness of Non-Negative Associative Gradient Projection Points over function minimizers in mini-batch sampled loss functions.
CoRR, 2019


  Loading...