Learning perturbation sets for robust machine learning Using generative modeling to capture real-world transformations from data for adversarial robustness Posted on July 20, 2020
Differentiable Convex Optimization Layers CVXPY creates powerful new PyTorch and TensorFlow layers Posted on October 28, 2019
Uniform convergence may be unable to explain generalization in deep learning Empirical and theoretical evidence demonstrating that uniform convergence based generalization bounds may be meaningless for overparameterized deep networks trained by stochastic gradient descent. Posted on July 9, 2019
Provable defenses against adversarial attacks Using ideas from linear programming and duality to create unbreakable, certified adversarial defenses Posted on March 12, 2019