Pith. sign in

REVIEW 4 cited by

DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule

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 2302.12022 v3 pith:QYEPAZX5 submitted 2023-02-08 cs.LG math.OC

classification cs.LGmath.OC
keywords gradientslearningsteptuneddistancedynamicformulaparameter-free
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a tuning-free dynamic SGD step size formula, which we call Distance over Gradients (DoG). The DoG step sizes depend on simple empirical quantities (distance from the initial point and norms of gradients) and have no ``learning rate'' parameter. Theoretically, we show that a slight variation of the DoG formula enjoys strong parameter-free convergence guarantees for stochastic convex optimization assuming only \emph{locally bounded} stochastic gradients. Empirically, we consider a broad range of vision and language transfer learning tasks, and show that DoG's performance is close to that of SGD with tuned learning rate. We also propose a per-layer variant of DoG that generally outperforms tuned SGD, approaching the performance of tuned Adam. A PyTorch implementation is available at https://github.com/formll/dog

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Clipping the Price of Adaptivity at the Tail

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    Under a model-loss decomposition, clipping model outputs in tail events yields adaptive SCO bounds matching known-parameter optima up to logarithmic factors in uncertainty.

  2. Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes

    math.OC 2024-12 unverdicted novelty 7.0 of 10

    Develops constant-stepsize and auto-conditioned projected gradient methods plus stochastic variants that achieve new iteration complexity bounds for finding approximate stationary points in nonconvex smooth optimization.

  3. Fantastic Pretraining Optimizers and Where to Find Them

    cs.LG 2025-09 conditional novelty 6.0 of 10

    After careful tuning, alternative optimizers speed up LLM pretraining by only 1.1x to 1.4x over AdamW, and the advantage shrinks with model scale.

  4. Scalable Hyperparameter-Divergent Ensemble Training with Automatic Learning Rate Exploration for Large Models

    cs.LG 2026-04 unverdicted novelty 5.0 of 10

    HDET lets data-parallel replicas explore a spread of learning rates independently before averaging parameters, with an auto-LR controller driven by inter-replica loss differences to produce a self-adapting schedule wi...

Pith tools