3 citations · 7 across the 8 of their papers we have counts for
8 papers
A Geometric View of Counterfactual Behavior: Interaction of Boundary Proximity and Local Support
Ioanna Gemou, Matteo Gamba, Randall Balestriero +1
Counterfactual explanations seek small, semantically meaningful changes to an input that alter a model's prediction, and are widely used to interpret and audit machine learning sys…
Improving Adversarial Robustness of Attribution via Implicit Regularization
Amir Mehrpanah, Matteo Gamba, Hossein Azizpour
The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expe…
Deep Probabilistic Supervision for Image Classification
Anton Adelöw, Matteo Gamba, Atsuto Maki
Supervised training of deep neural networks for classification typically relies on hard targets, which promote overconfidence and can limit calibration, generalization, and robustn…
On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations
Amir Mehrpanah, Matteo Gamba, Kevin Smith +1
ReLU networks, while prevalent for visual data, have sharp transitions, sometimes relying on individual pixels for predictions, making vanilla gradient-based explanations noisy and…
On the Lipschitz Constant of Deep Networks and Double Descent
Matteo Gamba, Hossein Azizpour, Mårten Björkman
Existing bounds on the generalization error of deep networks assume some form of smooth or bounded dependence on the input variable, falling short of investigating the mechanisms c…
Deep Double Descent via Smooth Interpolation
Matteo Gamba, Erik Englesson, Mårten Björkman +1
The ability of overparameterized deep networks to interpolate noisy data, while at the same time showing good generalization performance, has been recently characterized in terms o…
Are All Linear Regions Created Equal?
Matteo Gamba, Adrian Chmielewski-Anders, Josephine Sullivan +2
The number of linear regions has been studied as a proxy of complexity for ReLU networks. However, the empirical success of network compression techniques like pruning and knowledg…
Hyperplane Arrangements of Trained ConvNets Are Biased
Matteo Gamba, Stefan Carlsson, Hossein Azizpour +1
We investigate the geometric properties of the functions learned by trained ConvNets in the preactivation space of their convolutional layers, by performing an empirical study of h…