Hidden Boundary Motion in Transformer Optimization: Function-Space Orthogonalization of Affine Weight and Bias Updates

• URL: http://arxiv.org/abs/2607.22927v1
• Date: Fri, 24 Jul 2026 21:51:43 GMT
• Title: Hidden Boundary Motion in Transformer Optimization: Function-Space Orthogonalization of Affine Weight and Bias Updates
• Abstract summary: We call this hidden contribution emphboundary motion and decompose each update into a emphshape component and a shared emphboundary component.<n>In a single-seed experiment, SBO-AdamW raises validation accuracy from 81.68% to 85.81% and validation-selected test accuracy from 78.73% to 82.73%.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Weights and biases are normally optimized as separate parameter tensors, yet they do not represent separate functions when the input to an affine layer has nonzero mean. For an affine map $z=Wx+b$ with input mean $μ$, a weight update contains a sample-independent displacement $ΔWμ$ that is functionally indistinguishable from a bias update. We call this hidden contribution \emph{boundary motion} and decompose each update into a centered, sample-varying \emph{shape} component and a shared \emph{boundary} component. On a four-layer Transformer trained from scratch on IMDb, the bias-like term $g_bμ^\top$ has a median norm equal to 0.664 of the raw weight-gradient norm across affine layers and training checkpoints. More strikingly, the median ratio $\norm{ΔWμ}/\norm{Δb}$ is 134.7, while $\norm{ΔWμ}/\norm{Δb+ΔWμ}$ is 0.994. Thus, under AdamW, the observed boundary motion is almost entirely realized through the weight matrix rather than the explicit bias. We implement a diagnostic optimizer, Shape--Boundary Orthogonal AdamW (SBO-AdamW), that optimizes $g_W-g_bμ^\top$ and $g_b$ with independent Adam states and compensates the weight-induced boundary displacement. In a single-seed experiment, SBO-AdamW raises validation accuracy from 81.68\% to 85.81\% and validation-selected test accuracy from 78.73\% to 82.73\%, with the best validation checkpoint occurring at step 800 instead of step 3000. However, the moving-batch-center compensation produces severe bias-coordinate drift and strongly reduces boundary energy. The present evidence therefore supports hidden boundary motion as an important optimization mechanism, but it does not yet establish a final general-purpose optimizer. A stable centered-affine parameterization is identified as the required next step.

Related papers

• Same Flow, Different Paths: Variance Reduction in Flow Matching [67.12978375116599]
  We study the choice of this path from an optimization perspective.<n>Our main finding is that the choice of path $g_t$ can fundamentally change the convergence rate of SGD.
  arXiv  Detail & Related papers  (2026-09-15T15:01:04Z)
• Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks [29.66774607766935]
  Gradient surgery methods mitigate this issue by constructing directions from loss-specific gradients to reduce conflict before transformation.<n>Let $a_t$ denote the direction constructed by gradient surgery, $u_t$ the proposal, and $mathcalC_t$ the conflict-free gradient induced by the loss-specific gradients.<n>We propose Gradient-Update Alignment (GUA), which projects $u_t$ onto $mathcalC_t$ to obtain the aligned update $p_t$ and applies $p_t$ to the parameters.
  arXiv  Detail & Related papers  (2026-09-01T17:20:13Z)
• High-dimensional nonparametric changepoint detection via low-rank degree-two density projection [2.1991623402625606]
  We introduce a representation-based approach that retains all degree-at-most-two density information while replacing density estimation by matrix mean estimation.<n>Experiments with ambient dimension up to $200$, a three-change $d=100$ sequence, and a $128$-feature human-activity benchmark show that the method remains computationally practical.
  arXiv  Detail & Related papers  (2026-08-14T03:48:29Z)
• Joint Affine Spectral Shaping: Coupling Weight and Bias Updates Beyond Weight-Only Muon [11.323131201168572]
  Matrix spectrals reshape weight-update spectra but usually delegate vector-valued biases to a separate.<n>We formulate each affine layer as a joint momentum matrix $A=[M_W,m_b]$ and apply a capped regularized-inverse spectral map to the complete matrix.<n>A strict five-seed ablation on a four-layer BERT-mini trained from scratch on IMDb compares exact-SVD Muon, weight-only inverse shaping, affine-probe inverse shaping, and the proposed joint regularized inverse.
  arXiv  Detail & Related papers  (2026-08-04T01:08:33Z)
• Is Spurious Correlation Removal Always Learnable? [56.28155520961125]
  Invariant learning can fail even when the structure is statistically identifiable.<n>We show a conditional computational barrier: under a black-box samplable supervised sparse recovery primitive, there exist emphamplable multi-dimensional environments.<n>Synthetic and real datasets illustrate the predicted gaps and transitions and motivate simple diversity diagnostics.
  arXiv  Detail & Related papers  (2026-06-11T05:49:43Z)
• Bandit Convex Optimization with Gradient Prediction Adaptivity [56.816177049016794]
  We investigate whether optimistic gradient predictions can improve worst-case regret guarantees in a prediction-adaptive manner.<n>The key idea is a novel variance-reduced gradient estimator whose variance scales with the prediction error rather than the gradient norm.<n>We establish an information-theoretic lower bound that scales as $(sqrtmathbbE[S_T])$, providing a fundamental characterization of the best achievable prediction-adaptive regret.
  arXiv  Detail & Related papers  (2026-05-21T08:57:38Z)
• The Spectral Edge Thesis: A Mathematical Framework for Intra-Signal Phase Transitions in Neural Network Training [0.0]
  We show that phase transitions in neural network training are controlled by the spectral gap of the rolling-window Gram matrix of parameter updates.<n>Adiabatic parameter $mathcalA = |G|_F / (, g2)$ controls circuit stability: $mathcalA ll 1$ (plateau), $mathcalA sim 1$ (phase transition), $mathcalA gg 1$ (forgetting)
  arXiv  Detail & Related papers  (2026-03-30T20:10:22Z)
• Ghosts of Softmax: Complex Singularities That Limit Safe Step Sizes in Cross-Entropy [0.0]
  Cross-entropy training analyses rely on local Taylor models of the loss to predict whether a proposed step will decrease the objective.<n>We derive closed-form expressions under logit linearization along the proposed update direction.<n>Temperature scaling confirms the mechanism: normalizing by $_a$ shrinks the onset-threshold spread from standard deviation $0.992$ to $0.164$.
  arXiv  Detail & Related papers  (2026-03-13T19:42:12Z)
• OLion: Approaching the Hadamard Ideal by Intersecting Spectral and $\ell_{\infty}$ Implicit Biases [29.60546958677364]
  nameA combines spectral control from update directions with coordinate control from sign updates.<n>We prove convergence under a mild, empirically verified diagonal-isotropy assumption.<n>nameA matches or outperforms AdamW and Muon under comparable tuning while using only momentum-level state.
  arXiv  Detail & Related papers  (2026-02-01T08:59:45Z)
• Robust Layerwise Scaling Rules by Proper Weight Decay Tuning [50.11170157029911]
  In modern scale-invariant architectures, training quickly enters an degrading-governed steady state.<n>We introduce a weight-decay scaling rule for AdamW that preserves sublayer gain across widths.<n>Our results extend $mu$P beyond the near-init regime by explicitly controlling the steady-state scales set by parameters.
  arXiv  Detail & Related papers  (2025-10-17T02:58:35Z)
• Beyond likelihood ratio bias: Nested multi-time-scale stochastic approximation for likelihood-free parameter estimation [49.78792404811239]
  We study inference in simulation-based models where the analytical form of the likelihood is unknown.<n>We use a ratio-free nested multi-time-scale approximation (SA) method that simultaneously tracks the score and drives the parameter update.<n>We show that our algorithm can eliminate the original bias $Obig(sqrtfrac1Nbig)$ and accelerate the convergence rate from $Obig(beta_k+sqrtfracalpha_kNbig)$.
  arXiv  Detail & Related papers  (2024-11-20T02:46:15Z)
• Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition [71.33787410075577]
  We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses. We propose a new algorithm that attains an $widetildeO(dsqrtHS3K + sqrtHSAK)$ regret with high probability.
  arXiv  Detail & Related papers  (2024-03-07T15:03:50Z)
• Asynchronous Stochastic Optimization Robust to Arbitrary Delays [54.61797739710608]
  We consider optimization with delayed gradients where, at each time stept$, the algorithm makes an update using a stale computation - d_t$ for arbitrary delay $d_t gradient. Our experiments demonstrate the efficacy and robustness of our algorithm in cases where the delay distribution is skewed or heavy-tailed.
  arXiv  Detail & Related papers  (2021-06-22T15:50:45Z)
• A Simple Convergence Proof of Adam and Adagrad [74.24716715922759]
  We show a proof of convergence between the Adam Adagrad and $O(d(N)/st)$ algorithms. Adam converges with the same convergence $O(d(N)/st)$ when used with the default parameters.
  arXiv  Detail & Related papers  (2020-03-05T01:56:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.