Watts-per-Intelligence Part II: Algorithmic Catalysis
We develop a thermodynamic theory of algorithmic catalysis within the watts per intelligence framework, identifying reusable computational structures that reduce irreversible operations for a task class while satisfying bounded restoration and structural selectivity constraints. We prove that any class specific speed-up is upper-bounded by the algorithmic mutual information between the substrate and the class descriptor, and that encoding this information incurs a minimum thermodynamic cost via Landauer erasure. Combining these results yields a coupling theorem that lower-bounds the deployment horizon required for an algorithmic catalyst to be energetically favourable. The framework is illustrated on an affine SAT class and situates contemporary learned systems within an information thermodynamic constraint on intelligent computation.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Watts: Infrastructure for Open-Ended Learning
This paper proposes a framework called Watts for implementing, comparing, and recombining open-ended learning (OEL) algorithms. Motivated by modularity and algorithmic flexibility, Watts atomizes the components of OEL sy…
BenchmarkingAutocatalytic sets in polymer networks with variable catalysis distributions
All living systems -- from the origin of life to modern cells -- rely on a set of biochemical reactions that are simultaneously self-sustaining and autocatalytic. This notion of an autocatalytic set has been formalized g…
Catalysis distillation neural network for the few shot open catalyst challenge
The integration of artificial intelligence and science has resulted in substantial progress in computational chemistry methods for the design and discovery of novel catalysts. Nonetheless, the challenges of electrocataly…
Computational chemistryFew-Shot LearningGraph Neural NetworkLanguage ModellingWattsOnAI: Measuring, Analyzing, and Visualizing Energy and Carbon Footprint of AI Workloads
The rapid advancement of AI, particularly large language models (LLMs), has raised significant concerns about the energy use and carbon emissions associated with model training and inference. However, existing tools for …
BenchmarkingAn Atomistic Machine Learning Package for Surface Science and Catalysis
We present work flows and a software module for machine learning model building in surface science and heterogeneous catalysis. This includes fingerprinting atomic structures from 3D structure and/or connectivity informa…
Active LearningBIG-bench Machine Learning