PulseAugur
EN
LIVE 09:28:52

New compiler enables differentiable interpretation of Scheme programs

Researchers have developed a novel compiler that translates a subset of the Scheme programming language into differentiable computation graphs. This system enables differentiable meta-circular interpretation (DMCI), allowing gradients to be calculated for continuous constants embedded within programs executed by a compiled Scheme interpreter. The approach allows new programs to inherit differentiability without recompilation, supporting features like closures and recursion. DMCI has been demonstrated to be effective in co-searching programs and parameters for tasks such as predicting battery capacity fade and solving high-dimensional inverse problems, extending symbolic regression to executable, stateful programs. AI

IMPACT Enables direct optimization of generated code against data, potentially accelerating neurosymbolic AI development.

RANK_REASON The cluster contains an academic paper detailing a new method for program interpretation and optimization. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv cs.LG TIER_1 English(EN) · Lucas Sheneman ·

    Compile Once, Differentiate Everywhere: A Differentiable Meta-Circular Interpreter

    arXiv:2606.09930v1 Announce Type: cross Abstract: The boundary between program execution and gradient-based optimization has long limited the use of code itself as a learnable scientific model. We present a compiler that translates a self-hosting subset of Scheme into differentia…