activity
20182024
most citedRepeated Random Sampling for Minimizing the Time-to-Accuracy of Learning

7 citations · 16 across the 9 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

stat.ML2022★ 3 cited

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…

cs.LG2022★ 3 cited

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…