The Loss Does Not See the Basis, but Adam Does

• URL: http://arxiv.org/abs/2608.05136v1
• Date: Wed, 05 Aug 2026 17:56:26 GMT
• Title: The Loss Does Not See the Basis, but Adam Does
• Abstract summary: We show that gradient descent on a factored model $W = UVtop$ is implicitly biased toward low-rank solutions.<n>We then sort nine update rules on underdetermined matrix sensing by recovery error against the planted ground truth.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Gradient descent on a factored model $W = UV^\top$ is implicitly biased toward low-rank solutions, while Adam, starting from the same small initialization, is not. We trace the difference to the gauge symmetry of the loss, its invariance under $(U, V) \mapsto (UQ, VQ)$. Gradient flow's low-rank mechanism is available to an optimizer only if that optimizer is gauge-equivariant, a condition necessary for the transfer but not sufficient for low-rank recovery. Gradient descent, momentum, "shared-scalar" Adam, Muon, and Shampoo satisfy it. Adam, RMSProp, and the other coordinate-wise methods do not. A structure theorem characterizes the memoryless equivariant rules as exactly the Gram-determined left preconditioners, and a transfer theorem carries gradient flow's pathwise properties to common-scalar flows. We then sort nine update rules on underdetermined matrix sensing by recovery error against the planted ground truth. A one-parameter family from coordinate-wise to shared-scalar preconditioning restores the bias monotonically, isolating anisotropy as the cause. A "spectral schedule" reconciles two opposing reports about Muon: equal-rate updates recover exactly low-rank targets but lose their edge as the spectral tail grows. In transformers, Adam separates two gauge-equivalent initializations at the first step, where the equivariant optimizers stay at float precision, and ends with the per-head invariants $W_Q^\top W_K$ 56% apart in relative Frobenius distance, a gap no per-head rotation can close. On two hyperspectral datasets at matched training loss, gradient descent cuts held-out error by 43-44% at the lowest sampling density, and at lower effective rank. Basis choice is therefore not a tuning detail but a decision about which interpolant the optimizer selects.

Related papers

• EGGROLL, Unrolled: Understanding and Improving Low-Rank Evolution Strategies at Scale [9.562123195246393]
  EGGROLL makes evolution strategies practical for LLMs by replacing dense Gaussian weight perturbations with low-rank Gaussian products.<n>We analyze the error of its finite-population estimator.<n>LOO-ROLL, a leave-one-out estimator, preserves the finite-rank population field while replacing EGGROLL's two antithetic evaluations per direction by one.
  arXiv  Detail & Related papers  (2026-09-10T01:58:02Z)
• Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training [51.18425726646089]
  We propose textscSURE, a unified latent-space framework for image and video diffusion models.<n>It learns reward distributions and directly uses their reliability to guide dense post-training.<n>textscSURE-REFL achieves the highest VBench quality, semantic, and total scores among the evaluated methods.
  arXiv  Detail & Related papers  (2026-08-06T14:55:42Z)
• Attractor Geometry Determines the Identifiability Limits of System Discovery [0.764671395172401]
  We show that a single number, $_min(M)$, sets the identifiability ceiling for both sparse regression (SINDy) and evolutionary regression (PySR)<n>We also introduce Soft F1, a coefficient-weighted structural metric that resolves performance differences invisible to binary-success and predictive scores.
  arXiv  Detail & Related papers  (2026-07-20T20:19:19Z)
• Dead-Direction Conditioners: Gauge-Equivariant Preconditioning for Deep Networks [0.0]
  A deep network's loss is invariant to continuous symmetries of its parameters.<n>We build DDC, a Dead-Direction Conditioner that conditions the orbit decomposition of a $G$-invariant metric.<n>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.
  arXiv  Detail & Related papers  (2026-06-28T03:44:59Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• Dead Directions: Geometric Singular Learning [0.0]
  Singular learning theory and information geometry have studied the same parameter spaces in mostly separate vocabularies.<n>We bridge them through one primitive, the dead direction: a unit vector along which the Fisher metric degenerates.<n>A selection rule on smooth fibres translates this rate into Watanabe's single-direction contribution to the real log canonical threshold.<n>We then lift this rate to a deep network: a multi-layer K-FAC factorisation writes each Fisher block as a product of activation- and gradient-side rates.
  arXiv  Detail & Related papers  (2026-06-04T09:54:08Z)
• 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)
• Information Hidden in Gradients of Regression with Target Noise [2.8911861322232686]
  We show that the gradients alone can reveal the Hessian.<n>We provide non-asymptotic operator-norm guarantees under sub-Gaussian inputs.
  arXiv  Detail & Related papers  (2026-01-26T14:50:16Z)
• From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models [90.45197506653341]
  Large reasoning models generate intermediate reasoning traces before producing final answers.<n> aligning LRMs with human preferences, a crucial prerequisite for model deployment, remains underexplored.<n>A common workaround optimized a single sampled trajectory, which introduces substantial gradient variance from trace sampling.
  arXiv  Detail & Related papers  (2025-10-06T17:58:01Z)
• Transformers as Support Vector Machines [54.642793677472724]
  We establish a formal equivalence between the optimization geometry of self-attention and a hard-margin SVM problem. We characterize the implicit bias of 1-layer transformers optimized with gradient descent. We believe these findings inspire the interpretation of transformers as a hierarchy of SVMs that separates and selects optimal tokens.
  arXiv  Detail & Related papers  (2023-08-31T17:57:50Z)
• 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.