170 citations · 341 across the 11 of their papers we have counts for
3 papers · 1 filter
Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD
Konstantinos E. Nikolakakis, Farzin Haddadpour, Amin Karbasi +1
We provide sharp path-dependent generalization and excess risk guarantees for the full-batch Gradient Descent (GD) algorithm on smooth losses (possibly non-Lipschitz, possibly nonc…
Learning Distributionally Robust Models at Scale via Composite Optimization
Farzin Haddadpour, Mohammad Mahdi Kamani, Mehrdad Mahdavi +1
To train machine learning models that are robust to distribution shifts in the data, distributionally robust optimization (DRO) has been proven very effective. However, the existin…
Black-Box Generalization: Stability of Zeroth-Order Learning
Konstantinos E. Nikolakakis, Farzin Haddadpour, Dionysios S. Kalogerias +1
We provide the first generalization error analysis for black-box learning through derivative-free optimization. Under the assumption of a Lipschitz and smooth unknown loss, we cons…