I investigate the capability of small transformers to compute the greate...
We examine how transformers cope with two challenges: learning basic int...
Learning with Errors (LWE) is a hard math problem used in post-quantum
c...
We combine philosophical theories with quantitative analyses of online d...
The Learning With Errors (LWE) problem is one of the major hard problems...
A lattice of integers is the collection of all linear combinations of a ...
Traditional approaches to RL have focused on learning decision policies
...
This paper investigates the failure cases and out-of-distribution behavi...
Currently deployed public-key cryptosystems will be vulnerable to attack...
In this paper, we leverage low-level compiler intermediate representatio...
Symbolic regression, the task of predicting the mathematical expression ...
Symbolic regression, i.e. predicting a function from the observation of ...
We show that deep learning models, and especially architectures like the...
Most applications of transformers to mathematics, from integration to th...
With little to no parallel data available for programming languages,
uns...
Can advanced mathematical computations be learned from examples? Using
t...
Neural networks have a reputation for being better at solving statistica...