Uri Shaham

Understanding adversarial training: Increasing local stability of supervised models through robust optimization

Abstract We show that adversarial training of supervised learning models is in fact a robust optimization procedure. To do this, we establish a general framework for increasing local stability of supervised learning models using robust optimization. The framework is general and broadly applicable to differentiable non-parametric models, e.g., Artificial Neural Networks (ANNs). Using an alternating minimization-maximization procedure, the loss of the model is minimized with respect to perturbed examples that are generated at each parameter update, rather than with respect to the original training data. Our proposed framework generalizes adversarial training, as well as previous approaches for increasing local stability of ANNs. Experimental results reveal that our approach increases the robustness of the network to existing adversarial examples, while making it harder to generate new ones. Furthermore, our algorithm improves the accuracy of the networks also on the original test data.

Provable approximation properties for deep neural networks

We discuss approximation of functions using deep neural nets. Given a function

Removal of batch effects using distribution-matching residual networks

f

DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network

on a

Gating mass cytometry data by deep learning

d

Learning by coincidence: Siamese networks and common variable learning

-dimensional manifold

Batch Effect Removal via Batch-Free Encoding

\Gamma \subset \mathbb{R}^m

Methods for detecting co-mutated pathways in cancer samples to inform treatment selection

, we construct a sparsely-connected depth-4 neural network and bound its error in approximating

DeepCyTOF: Automated Cell Classification of Mass Cytometry Data by Deep Learning and Domain Adaptation

f

Deep Survival: A Deep Cox Proportional Hazards Network.

. The size of the network depends on dimension and curvature of the manifold