no code implementations • 10 Oct 2022 • Giuseppe Castiglione, Ga Wu, Christopher Srinivasa, Simon Prince
We propose a novel criterion for evaluating individual fairness and develop a practical testing method based on this criterion which we call fAux (pronounced fox).
no code implementations • 7 Jul 2022 • Dhananjay Ashok, Vineel Nagisetty, Christopher Srinivasa, Vijay Ganesh
We present a novel hybrid algorithm for training Deep Neural Networks that combines the state-of-the-art Gradient Descent (GD) method with a Mixed Integer Linear Programming (MILP) solver, outperforming GD and variants in terms of accuracy, as well as resource and data efficiency for both regression and classification tasks.
no code implementations • 5 Apr 2022 • Amir Khoshaman, Giuseppe Castiglione, Christopher Srinivasa
We explore training Binary Neural Networks (BNNs) as a discrete variable inference problem over a factor graph.
no code implementations • 31 Mar 2022 • Giuseppe Castiglione, Gavin Ding, Masoud Hashemi, Christopher Srinivasa, Ga Wu
Adversarial robustness is one of the essential safety criteria for guaranteeing the reliability of machine learning models.
no code implementations • 2 Mar 2022 • Ga Wu, Masoud Hashemi, Christopher Srinivasa
It then complements the negative impact of removing marked data by reweighting the remaining data optimally.
no code implementations • 23 Aug 2019 • Christopher G. Blake, Giuseppe Castiglione, Christopher Srinivasa, Marcus Brubaker
The problem of efficiently training and evaluating image classifiers that can distinguish between a large number of object categories is considered.
no code implementations • NIPS Workshop CDNNRIA 2018 • Christopher Blake, Luyu Wang, Giuseppe Castiglione, Christopher Srinivasa, Marcus Brubaker
Pruning neural networks for wiring length efficiency is considered.
no code implementations • NeurIPS 2017 • Christopher Srinivasa, Inmar Givoni, Siamak Ravanbakhsh, Brendan J. Frey
We study the application of min-max propagation, a variation of belief propagation, for approximate min-max inference in factor graphs.