Pith. sign in

REVIEW 6 cited by

Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.02244 v5 pith:UWKERGVL submitted 2023-10-03 cs.NE cond-mat.dis-nnmath.PR

classification cs.NEcond-mat.dis-nnmath.PR
keywords networksfeatureblockdepthwisediversityempiricallylearningneural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

By classifying infinite-width neural networks and identifying the *optimal* limit, Tensor Programs IV and V demonstrated a universal way, called $\mu$P, for *widthwise hyperparameter transfer*, i.e., predicting optimal hyperparameters of wide neural networks from narrow ones. Here we investigate the analogous classification for *depthwise parametrizations* of deep residual networks (resnets). We classify depthwise parametrizations of block multiplier and learning rate by their infinite-width-then-depth limits. In resnets where each block has only one layer, we identify a unique optimal parametrization, called Depth-$\mu$P that extends $\mu$P and show empirically it admits depthwise hyperparameter transfer. We identify *feature diversity* as a crucial factor in deep networks, and Depth-$\mu$P can be characterized as maximizing both feature learning and feature diversity. Exploiting this, we find that absolute value, among all homogeneous nonlinearities, maximizes feature diversity and indeed empirically leads to significantly better performance. However, if each block is deeper (such as modern transformers), then we find fundamental limitations in all possible infinite-depth limits of such parametrizations, which we illustrate both theoretically and empirically on simple networks as well as Megatron transformer trained on Common Crawl.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DeepLoop: Depth Scaling for Looped Transformers

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Looped Transformers need residual-scaling exponent p=1/2 instead of DeepNorm's 1/4 when shared blocks are revisited with aligned visit-wise gradients.

  2. Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    Splitting weight matrices into a fixed-norm direction and learnable per-row/column magnitudes improves LLM training over AdamW/Muon, removes weight decay and warmup, and transfers the optimal LR across width.

  3. Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Falcon-H1 reports competitive benchmark scores for a 0.5B to 34B family of parallel hybrid attention/Mamba-2 models, claiming 2x to 4x parameter efficiency versus dense transformers.

  4. Scale Weight Decay and Train Better

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Muon with weight decay scaled by η/η_max reaches the same MoE validation loss ~30% faster than constant-decay Muon while preserving asymptotic stationarity of the unregularized objective.

  5. SingLoRA: Low Rank Adaptation Using a Single Matrix

    cs.AI 2025-07 conditional novelty 5.0 of 10

    SingLoRA replaces LoRA's two matrices A and B with one matrix A and the symmetric update AA^T, cutting adapter parameters roughly in half while claiming more stable fine-tuning.

  6. Sub-Scaling Laws: On the Role of Data Density and Training Strategies in LLMs

    cs.LG 2025-07 conditional novelty 4.0 of 10

    High data redundancy and over-training decelerate LLM performance gains, and the authors fit a sub-optimal scaling law with logistic correction terms to predict the slowdown.

Pith tools