3 citations · 3 across the 9 of their papers we have counts for
Showing 2025Show all
3 papers · 1 filter
stat.ML2025
When Models Don't Collapse: On the Consistency of Iterative MLE
Daniel Barzilai, Ohad Shamir
The widespread use of generative models has created a feedback loop, in which each generation of models is trained on data partially produced by its predecessors. This process has…
math.OC2025
Are Convex Optimization Curves Convex?
Guy Barzilai, Ohad Shamir, Moslem Zamani
In this paper, we study when we might expect the optimization curve induced by gradient descent to be \emph{convex} -- precluding, for example, an initial plateau followed by a sha…
cs.LG2025
Beyond Benign Overfitting in Nadaraya-Watson Interpolators
Daniel Barzilai, Guy Kornowski, Ohad Shamir
In recent years, there has been much interest in understanding the generalization behavior of interpolating predictors, which overfit on noisy training data. Whereas standard analy…