most citedPUMA: Performance Unchanged Model Augmentation for Training Data Removal

11 citations · 12 across the 4 of their papers we have counts for

collaborators

5 papers

stat.ML20221 cited

fAux: Testing Individual Fairness via Gradient Alignment

Giuseppe Castiglione, Ga Wu, Christopher Srinivasa +1

Machine learning models are vulnerable to biases that result in unfair treatment of individuals from different populations. Recent work that aims to test a model's fairness at the…

cs.LG2022

Nonlocal optimization of binary neural networks

Amir Khoshaman, Giuseppe Castiglione, Christopher Srinivasa

We explore training Binary Neural Networks (BNNs) as a discrete variable inference problem over a factor graph. We study the behaviour of this conversion in an under-parameterized…

stat.ML2022

Scalable Whitebox Attacks on Tree-based Models

Giuseppe Castiglione, Gavin Ding, Masoud Hashemi +2

Adversarial robustness is one of the essential safety criteria for guaranteeing the reliability of machine learning models. While various adversarial robustness testing approaches…

stat.ML202211 cited

PUMA: Performance Unchanged Model Augmentation for Training Data Removal

Ga Wu, Masoud Hashemi, Christopher Srinivasa

Preserving the performance of a trained model while removing unique characteristics of marked training data points is challenging. Recent research usually suggests retraining a mod…

cs.LG2019

Parity Partition Coding for Sharp Multi-Label Classification

Christopher G. Blake, Giuseppe Castiglione, Christopher Srinivasa +1

The problem of efficiently training and evaluating image classifiers that can distinguish between a large number of object categories is considered. A novel metric, sharpness, is p…