Hyperparameter Transfer Laws for Non-Recurrent Multi-Path Neural Networks
Deeper modern architectures are costly to train, making hyperparameter transfer preferable to expensive repeated tuning. Maximal Update Parametrization ($μ$P) helps explain why many hyperparameters transfer across width. Yet depth scaling is less understood for modern architectures, whose computation graphs contain multiple parallel paths and residual aggregation. To unify various non-recurrent multi-path neural networks such as CNNs, ResNets, and Transformers, we introduce a graph-based notion of effective depth. Under stabilizing initializations and a maximal-update criterion, we show that the optimal learning rate decays with effective depth following a universal -3/2 power law. Here, the maximal-update criterion maximizes the typical one-step representation change at initialization without causing instability, and effective depth is the minimal path length from input to output, counting layers and residual additions. Experiments across diverse architectures confirm the predicted slope and enable reliable zero-shot transfer of learning rates across depths and widths, turning depth scaling into a predictable hyperparameter-transfer problem.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A comparative study of transformer models and recurrent neural networks for path-dependent composite materials
Accurate modeling of Short Fiber Reinforced Composites (SFRCs) remains computationally expensive for full-field simulations. Data-driven surrogate models using Artificial Neural Networks (ANNs) have been proposed as an e…
Deriving Hyperparameter Scaling Laws via Modern Optimization Theory
Hyperparameter transfer has become an important component of modern large-scale training recipes. Existing methods, such as muP, primarily focus on transfer between model sizes, with transfer across batch sizes and train…
Scaling Optimal LR Across Token Horizons
State-of-the-art LLMs are powered by scaling -- scaling model size, dataset size and cluster size. It is economically infeasible to extensively tune hyperparameter for the largest runs. Instead, approximately optimal hyp…
$μ$pscaling small models: Principled warm starts and hyperparameter transfer
Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve efficiency, recent work has explored model upscaling: initializing larger models fr…
Recurrent networks improve neural response prediction and provide insights into underlying cortical circuits
Feedforward CNN models have proven themselves in recent years as state-of-the-art models for predicting single-neuron responses to natural images in early visual cortical neurons. In this paper, we extend these models wi…