24 citations · 27 across the 5 of their papers we have counts for
6 papers
Latent Space Factorization in LoRA
Shashi Kumar, Yacouba Kaloga, John Mitros +2
Low-rank adaptation (LoRA) is a widely used method for parameter-efficient finetuning. However, existing LoRA variants lack mechanisms to explicitly disambiguate task-relevant info…
Generalization vs. Memorization in the Presence of Statistical Biases in Transformers
John Mitros
This study aims to understand how statistical biases affect the model's ability to generalize to in-distribution and out-of-distribution data on algorithmic tasks. Prior research i…
On the Importance of Regularisation & Auxiliary Information in OOD Detection
John Mitros, Brian Mac Namee
Neural networks are often utilised in critical domain applications (e.g. self-driving cars, financial markets, and aerospace engineering), even though they exhibit overconfident pr…
Ramifications of Approximate Posterior Inference for Bayesian Deep Learning in Adversarial and Out-of-Distribution Settings
John Mitros, Arjun Pakrashi, Brian Mac Namee
Deep neural networks have been successful in diverse discriminative classification tasks, although, they are poorly calibrated often assigning high probability to misclassified pre…
On the Validity of Bayesian Neural Networks for Uncertainty Estimation
John Mitros, Brian Mac Namee
Deep neural networks (DNN) are versatile parametric models utilised successfully in a diverse number of tasks and domains. However, they have limitations---particularly from their…
A Categorisation of Post-hoc Explanations for Predictive Models
John Mitros, Brian Mac Namee
The ubiquity of machine learning based predictive models in modern society naturally leads people to ask how trustworthy those models are? In predictive modeling, it is quite commo…