Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks
Mirrored from arXiv — Machine Learning for archival readability. Support the source by reading on the original site.
Computer Science > Machine Learning
Title:Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks
Abstract:A deep network's loss is invariant to continuous symmetries of its parameters: the logit shift, the ReLU rescaling, the LayerNorm scale, the per-head attention rotation. Adam's per-coordinate preconditioner drifts along each symmetry orbit, which pulls the trajectory off the symmetry quotient where the optimization lives and blurs the singular-learning rate the quotient makes readable. We build DDC, a Dead-Direction Conditioner that lifts a base optimizer into a $G$-equivariant one: it conditions the optimizer's state in the orbit decomposition of a $G$-invariant metric, so the trajectory stays a preconditioned gradient flow on the quotient $\bar\Theta = \Theta/G$. The construction carries four architectural gauges (cross-entropy shift, ReLU and SwiGLU rescaling, LayerNorm and RMSNorm scale, and a per-head $O(d_{\rm head})$ attention rotation matched to RoPE), proves exactly equivariant on an Adam base, and composes with a Muon base through a gauge-equivariant orthogonaliser. Respecting the symmetry changes both the minimum the optimizer reaches and what it leaves measurable there. On a language model trained past the point of fit, DDCAdam resists the over-training collapse AdamW falls into, holding a validation-train loss gap of 0.67 against 5.88, and reads the dead-direction rate in 32 of 65 layer-by-observable cells where AdamW reads it in 7. A vision transformer trained from scratch reaches lower validation loss (1.71 against 2.12) while compressing spare feed-forward capacity a matched AdamW leaves intact. On a Muon base, where the rotation gauge composes exactly, DDCMuon groks ten of eleven seeds at depth 24 that a plain Muon never reaches. Built into the optimizer, a network's gauge symmetry sharpens the minimum it finds and turns that minimum's geometry into something the trajectory can measure.
| Comments: | 69 pages, 28 figures, 9 tables. Builds the gauge-equivariant preconditioner left open in arXiv:2606.05957 |
| Subjects: | Machine Learning (cs.LG); Differential Geometry (math.DG); Optimization and Control (math.OC); Machine Learning (stat.ML) |
| MSC classes: | 68T07 (Primary), 90C26, 62B11 |
| ACM classes: | I.2.6; G.1.6 |
| Cite as: | arXiv:2606.29176 [cs.LG] |
| (or arXiv:2606.29176v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2606.29176
arXiv-issued DOI via DataCite (pending registration)
|
Submission history
From: Tejas Pradeep Shirodkar [view email][v1] Sun, 28 Jun 2026 03:44:59 UTC (565 KB)
Access Paper:
- View PDF
- HTML (experimental)
- TeX Source
Current browse context:
References & Citations
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
More from arXiv — Machine Learning
-
Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models
Jun 30
-
On the Necessity of a Liquid Substrate for Mesh Intelligence
Jun 30
-
Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy
Jun 30
-
Learning to Distributedly Estimate under Partially Known Dynamics: A Covariance-Agnostic Neural Kalman Consensus Filter
Jun 30
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.