Gal Yehuda

activity

20162026

most citedIt's Not What Machines Can Learn, It's What We Cannot Teach

8 citations · 16 across the 12 of their papers we have counts for

collaborators

Showing 2023Show all

2 papers · 1 filter

cs.DS2023

Geometric Covering using Random Fields

Felipe Goncalves, Daniel Keren, Amit Shahar +1

A set of vectors $S \subseteq R^{d}$ is $(k_{1}, ε)$ -clusterable if there are $k_{1}$ balls of radius $ε$ that cover $S$ . A set of vectors $S \subseteq \mathb…

cs.LG2023

Probabilistic Invariant Learning with Randomized Linear Classifiers

Leonardo Cotta, Gal Yehuda, Assaf Schuster +1

Designing models that are both expressive and preserve known invariances of tasks is an increasingly hard problem. Existing solutions tradeoff invariance for computational or memor…