Adaptive Neural Compilation
This work addresses program optimization for specific data distributions, offering a novel approach but is incremental as it builds on differentiable program representations.
The paper tackles the problem of efficient program learning by proposing an adaptive neural-compilation framework that optimizes programs for a target input distribution, achieving a high success rate in learning specifically-tuned algorithms.
This paper proposes an adaptive neural-compilation framework to address the problem of efficient program learning. Traditional code optimisation strategies used in compilers are based on applying pre-specified set of transformations that make the code faster to execute without changing its semantics. In contrast, our work involves adapting programs to make them more efficient while considering correctness only on a target input distribution. Our approach is inspired by the recent works on differentiable representations of programs. We show that it is possible to compile programs written in a low-level language to a differentiable representation. We also show how programs in this representation can be optimised to make them efficient on a target distribution of inputs. Experimental results demonstrate that our approach enables learning specifically-tuned algorithms for given data distributions with a high success rate.