Pith. sign in

REVIEW 5 cited by

Dying ReLU and Initialization: Theory and Numerical Examples

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 1903.06733 v3 pith:VCXEXNUL submitted 2019-03-15 stat.ML cs.LGmath.PR

classification stat.MLcs.LGmath.PR
keywords reluinitializationdyingprocedureexamplesneuronsnumericalprobability
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The dying ReLU refers to the problem when ReLU neurons become inactive and only output 0 for any input. There are many empirical and heuristic explanations of why ReLU neurons die. However, little is known about its theoretical analysis. In this paper, we rigorously prove that a deep ReLU network will eventually die in probability as the depth goes to infinite. Several methods have been proposed to alleviate the dying ReLU. Perhaps, one of the simplest treatments is to modify the initialization procedure. One common way of initializing weights and biases uses symmetric probability distributions, which suffers from the dying ReLU. We thus propose a new initialization procedure, namely, a randomized asymmetric initialization. We prove that the new initialization can effectively prevent the dying ReLU. All parameters required for the new initialization are theoretically designed. Numerical examples are provided to demonstrate the effectiveness of the new initialization procedure.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. The Map Behind the Flow: Finite-Step Gradient Descent as a Dynamical System

    cs.LG 2026-07 accept novelty 7.0 of 10

    The edge of stability is the first bifurcation of the finite-step gradient map; residual oscillations then drive balancing and representation selection beyond that edge.

  2. Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks

    cs.LG 2025-08 conditional novelty 6.0 of 10

    An initialization that maximizes a semi-orthogonal weight matrix's alignment with the all-ones vector prevents dying ReLU and keeps 100-layer ReLU networks trainable.

  3. STAR-Pose: Efficient Low-Resolution Video Human Pose Estimation via Spatial-Temporal Adaptive Super-Resolution

    cs.CV 2025-06 conditional novelty 6.0 of 10

    STAR-Pose combines a spatial-temporal transformer with linear attention, a CNN texture branch, and a pose-aware loss to estimate human pose from low-resolution video, reporting up to 5.2% mAP improvement at 64x48.

  4. 4D-MISR: A unified model for low-dose super-resolution imaging via feature fusion

    cs.CV 2025-07 reject novelty 5.0 of 10

    4D-MISR maps low-dose, multi-view virtual bright-field 4D-STEM data to high-resolution images using a CNN trained on simulated specimens, but the evaluation may be compromised by missing train/test separation.

  5. TinyProto: Communication-Efficient Federated Learning with Sparse Prototypes in Resource-Constrained Environments

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Compressing class prototypes with per-class masks and a sample-count scaling trick cuts communication cost in prototype-based federated learning by up to several times without hurting accuracy.

Pith tools