Philip M. Long

Latest

• Deep linear networks can benignly overfit when shallow ones do
• Foolish crowds support benign overfitting
• The interplay between implicit bias and benign overfitting in two-layer linear networks
• When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations?
• When does gradient descent with logistic loss find interpolating two-layer networks?
• Finite-sample analysis of interpolating linear classifiers in the overparameterized regime
• Oracle lower bounds for stochastic gradient Markov chain Monte Carlo methods