Newshot
Papers Still developing Event #01M7J58J2RRVZ999NCJZBV2R9Q

Watch Your Step: Adam's Margin Maximization Bias Depends on the Learning Rate Schedule

Event overview(model summary, not the source's own text)

A revised arXiv paper (2611.01929v2) examines the implicit bias of the Adam optimizer and how closely it resembles sign gradient descent on homogeneous models in binary classification. The paper's headline claim is that Adam's margin maximization bias depends on the learning rate schedule. No experimental figures, model names, or datasets are given in the available abstract text, and the work is presented as an abstract-level preprint with no stated follow-up.

This summary was distilled by a model from the 3 reports below; it is not the source text. Treat the reports themselves as the facts.

How this story unfolded

Left: what it concluded — the key points the model distilled from the reports below, each one listing the reports it rests on. Right: what happened — ordered by time, each with a short summary so you can follow the thread without clicking through. The numbered links work both ways: tap a source under a point to jump to that report, tap the cited-by chip on a report to jump back to the point.

Key points3 items Model summary · ordered by when the evidence was published

  1. Point 01 11/16, 13:00

    arXiv paper 2611.01929v2 is a replacement submission studying Adam's implicit bias.

  2. Point 02 11/16, 13:00

    The work compares Adam with sign gradient descent on homogeneous models in binary classification.

  3. Point 03 11/16, 13:00

    The paper argues Adam's margin maximization bias depends on the learning rate schedule.

ReportsBy publish time · newer further down

  1. November 16, 2026 · Mon
  2. Start

    Watch Your Step: Adam's Margin Maximization Bias Depends on the Learning Rate Schedule

    Original summary arXiv:2611.01929v2 Announce Type: replace-cross Abstract: We study the implicit bias of Adam and its similarity to sign gradient descent on homogeneous models in binary classificat

    arXiv stat.ML Original ↗
  3. November 18, 2026 · Wed
  4. +2d 0h

    Hybrid Quantum Selection of Learning Rates in Language-Model Training: Termination Criteria and an Interaction-Guided Schedule Oracle

    Original summary arXiv:2611.21701v1 Announce Type: new Abstract: Learning-rate choices strongly affect language-model fine-tuning, but the best joint profile across layer groups is generally unknow

    arXiv cs.LG Original ↗
  5. +2d 0h

    CueSplat: Learning to Schedule Sparse Deformation for Dynamic Gaussian Splatting on Edge Devices

    Original summary arXiv:2611.22095v1 Announce Type: new Abstract: Deformation-based 4D Gaussian splatting (4DGS) enables dynamic scene rendering. However, evaluating deformation networks for all Gau

    arXiv cs.CV Original ↗
  6. Still developing · later reports will keep extending this axis