Abstract--Kurtosis-based Independent Component Analysis (ICA) weakens in wide, balanced mixtures. We also show that purification--selecting m R sign-consistent sources--restores R-independent contrast Ω(1/m), with a simple data-driven heuristic. Synthetic experiments validate the predicted decay, the T crossover, and contrast recovery. Independent Component Analysis (ICA) recovers statistically independent latent sources from linear mixtures and is identifiable whenever at most one source is Gaussian [1]. Excess kurtosis--the standardized fourth cumulant--is a central contrast function [9], and kurtosis-type nonlinearities remain standard in FastICA.

Layer normalization has demonstrated remarkable effectiveness at preventing plasticity loss in continual and reinforcement learning (RL), though the precise reasons for this effectiveness remain mysterious.

We explain the discrepancy by reproducing the Kaplan et al. scaling law on two datasets (OpenWebText2 and RefinedWeb)

Despite the fact that experimental neural scaling laws have substantially guided empirical progress in large-scale machine learning, no existing theory can quantitatively predict the exponents of these important laws for any modern LLM trained on any natural language dataset. We provide the first such theory in the case of data-limited scaling laws. We isolate two key statistical properties of language that alone can predict neural scaling exponents: (i) the decay of pairwise token correlations with time separation between token pairs, and (ii) the decay of the next-token conditional entropy with the length of the conditioning context. We further derive a simple formula in terms of these statistics that predicts data-limited neural scaling exponents from first principles without any free parameters or synthetic data models. Our theory exhibits a remarkable match with experimentally measured neural scaling laws obtained from training GPT-2 and LLaMA style models from scratch on two qualitatively different benchmarks, TinyStories and WikiText.

Understanding convergence of stochastic gradient descent (SGD) based optimization algorithms can help deal with enormous machine learning problems.