no code implementations • 14 Feb 2023 • Tony T. Wang, Igor Zablotchi, Nir Shavit, Jonathan S. Rosenfeld
We conduct an in-depth investigation of foundation-model cliff-learning and study toy models of the phenomenon.
no code implementations • 17 Aug 2021 • Jonathan S. Rosenfeld
Running faster will only get you so far -- it is generally advisable to first understand where the roads lead, then get a car ...
no code implementations • 18 Jun 2020 • Jonathan S. Rosenfeld, Jonathan Frankle, Michael Carbin, Nir Shavit
We show that the error of iteratively magnitude-pruned networks empirically follows a scaling law with interpretable coefficients that depend on the architecture and task.
no code implementations • 16 Dec 2019 • Dan Schmidt, Nick Moran, Jonathan S. Rosenfeld, Jonathan Rosenthal, Jonathan Yedidia
The AlphaZero algorithm for the learning of strategy games via self-play, which has produced superhuman ability in the games of Go, chess, and shogi, uses a quantitative reward function for game outcomes, requiring the users of the algorithm to explicitly balance different components of the reward against each other, such as the game winner and margin of victory.
no code implementations • ICLR 2020 • Jonathan S. Rosenfeld, Amir Rosenfeld, Yonatan Belinkov, Nir Shavit
In this work, we present a functional form which approximates well the generalization error in practice.