Pith. sign in

REVIEW 4 cited by

Why are Adaptive Methods Good for Attention Models?

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 1912.03194 v2 pith:5BYC2EYA submitted 2019-12-06 math.OC cs.LG

classification math.OCcs.LG
keywords adaptivegradientmethodsclippingheavy-tailednoisealgorithmattention
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While stochastic gradient descent (SGD) is still the \emph{de facto} algorithm in deep learning, adaptive methods like Clipped SGD/Adam have been observed to outperform SGD across important tasks, such as attention models. The settings under which SGD performs poorly in comparison to adaptive methods are not well understood yet. In this paper, we provide empirical and theoretical evidence that a heavy-tailed distribution of the noise in stochastic gradients is one cause of SGD's poor performance. We provide the first tight upper and lower convergence bounds for adaptive gradient methods under heavy-tailed noise. Further, we demonstrate how gradient clipping plays a key role in addressing heavy-tailed gradient noise. Subsequently, we show how clipping can be applied in practice by developing an \emph{adaptive} coordinate-wise clipping algorithm (ACClip) and demonstrate its superior performance on BERT pretraining and finetuning tasks.

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. Gradient Clipping Beyond Vector Norms: A Spectral Approach for Matrix-Valued Parameters

    cs.LG 2026-05 unverdicted novelty 7.0 of 10

    Spectral clipping of leading singular values in gradient matrices stabilizes SGD for non-convex problems with heavy-tailed noise and achieves the optimal convergence rate O(K^{(2-2α)/(3α-2)}).

  2. Adaptive Federated Optimization

    cs.LG 2020-02 unverdicted novelty 6.0 of 10

    Proposes federated adaptive optimizers (FedAdagrad, FedAdam, FedYogi) with convergence analysis for non-convex objectives under data heterogeneity and reports empirical gains over FedAvg.

  3. On the Performance of Differentially Private Optimization with Heavy-Tail Class Imbalance

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Under heavy-tail class imbalance, subtracting the DP noise variance from Adam's second moment (DP-AdamBC) substantially improves learning of rare classes compared with DP gradient descent.

  4. Perspectives on Tsallis Statistics for Artificial Intelligence

    cs.AI 2026-08 conditional novelty 3.0 of 10

    Independent AI methods, including sparsemax attention, Tsallis-entropy reinforcement learning, Student-t generative models, and robust losses, are instances of a single 'q-dial' deformation of Boltzmann-Gibbs statisti...

Pith tools