Search Results for author:
Found 5 papers, 0 papers with code
Cliff-Learning
We conduct an in-depth investigation of foundation-model cliff-learning and study toy models of the phenomenon.
Scaling Laws for Deep Learning
Running faster will only get you so far -- it is generally advisable to first understand where the roads lead, then get a car ...
On the Predictability of Pruning Across Scales
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.
Self-Play Learning Without a Reward Metric
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.
A Constructive Prediction of the Generalization Error Across Scales
In this work, we present a functional form which approximates well the generalization error in practice.
