In the algorithmic (Kolmogorov) view, agents are programs that track and compress sensory streams using generative programs. We propose a framework where the relevant structural prior is simplicity (Solomonoff) understood as \emph{compositional symmetry}: natural streams are well described by (local) actions of finite-parameter Lie pseudogroups on geometrically and topologically complex low-dimensional configuration manifolds (latent spaces). Modeling the agent as a generic neural dynamical system coupled to such streams, we show that accurate world-tracking imposes (i) \emph{structural constraints} -- equivariance of the agent's constitutive equations and readouts -- and (ii) \emph{dynamical constraints}: under static inputs, symmetry induces conserved quantities (Noether-style labels) in the agent dynamics and confines trajectories to reduced invariant manifolds; under slow drift, these manifolds move but remain low-dimensional. This yields a hierarchy of reduced manifolds aligned with the compositional factorization of the pseudogroup, providing a geometric account of the ``blessing of compositionality'' in deep models. We connect these ideas to the Spencer formalism for Lie pseudogroups and formulate a symmetry-based, self-contained version of predictive coding in which higher layers receive only \emph{coarse-grained residual transformations} (prediction-error coordinates) along symmetry directions unresolved at lower layers.
翻译:在算法(柯尔莫哥洛夫)视角下,智能体是通过生成程序追踪并压缩感知流的程序。我们提出一个框架,其中相关的结构先验是简洁性(所罗门诺夫),其被理解为组合对称性:自然流可通过有限参数李伪群在几何与拓扑结构复杂的低维构型流形(潜空间)上的(局部)作用得到良好描述。将智能体建模为耦合于此类流的通用神经动力系统,我们证明精确的世界追踪施加了(i)结构约束——智能体本构方程与读出函数的等变性,以及(ii)动力学约束:在静态输入下,对称性在智能体动力学中诱导出守恒量(诺特式标签)并将轨迹限制在约化的不变流形上;在缓慢漂移下,这些流形会发生移动但保持低维性。由此产生与伪群组合分解对齐的约化流形层次结构,为深度模型中“组合性优势”提供了几何解释。我们将这些思想与李伪群的斯宾塞形式体系相联系,并构建了一种基于对称性的自洽预测编码版本,其中高层仅接收沿低层未解析对称方向的粗粒度残差变换(预测误差坐标)。