Pith. sign in

REVIEW 7 cited by

Methods for Convex (L₀,L₁)-Smooth Optimization: Clipping, Acceleration, and Adaptivity

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 2409.14989 v2 pith:GJVJ2WLH submitted 2024-09-23 math.OC cs.LG

Methods for Convex (L₀,L₁)-Smooth Optimization: Clipping, Acceleration, and Adaptivity

classification math.OC cs.LG
keywords gradientconvergenceconvexderivedescentoptimizationratessmooth
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Due to the non-smoothness of optimization problems in Machine Learning, generalized smoothness assumptions have been gaining a lot of attention in recent years. One of the most popular assumptions of this type is $(L_0,L_1)$-smoothness (Zhang et al., 2020). In this paper, we focus on the class of (strongly) convex $(L_0,L_1)$-smooth functions and derive new convergence guarantees for several existing methods. In particular, we derive improved convergence rates for Gradient Descent with (Smoothed) Gradient Clipping and for Gradient Descent with Polyak Stepsizes. In contrast to the existing results, our rates do not rely on the standard smoothness assumption and do not suffer from the exponential dependency from the initial distance to the solution. We also extend these results to the stochastic case under the over-parameterization assumption, propose a new accelerated method for convex $(L_0,L_1)$-smooth optimization, and derive new convergence rates for Adaptive Gradient Descent (Malitsky and Mishchenko, 2020).

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

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

  1. Stochastic Non-Smooth Convex Optimization with Unbounded Gradients

    math.OC 2026-05 unverdicted novelty 8.0

    Introduces generalized Lipschitz class and shows clipped AdamW outperforms SGD and AdaGrad for stochastic convex optimization under this and related assumptions.

  2. Stochastic Non-Smooth Convex Optimization with Unbounded Gradients

    math.OC 2026-05 unverdicted novelty 7.0

    Clipped AdamW with exponentially weighted accumulation achieves superior global convergence rates for convex stochastic generalized Lipschitz optimization compared to SGD and AdaGrad.

  3. Normalized First-Order Methods for Convex (L0, L1)-Smooth Optimization with Inexact Gradients

    math.OC 2026-07 conditional novelty 5.0

    Comparison-oracle variants of NGD and Polyak GD converge for convex (L0, L1)-smooth objectives when the normalized-gradient error δ is bounded by explicit O(√ε)-scale thresholds.

  4. Non-Euclidean SGD for Structured Optimization: Unified Analysis and Improved Rates

    math.OC 2025-11 conditional novelty 5.0

    Non-Euclidean SGD variants (SignSGD, Muon) provably match adaptive optimizers' convergence rates under structured smoothness and noise assumptions.

  5. Frank-Wolfe Algorithms for (L0, L1)-smooth functions

    math.OC 2025-10 unverdicted novelty 5.0

    Proposes (L0, L1)-Frank-Wolfe and adaptive variant claiming superior convergence rates for (L0, L1)-smooth objectives over classical Frank-Wolfe.

  6. Frank-Wolfe Algorithms for (L0, L1)-smooth functions

    math.OC 2025-10 unverdicted novelty 5.0

    A new (L0, L1)-Frank-Wolfe algorithm and its adaptive version are proposed for (L0, L1)-smooth optimization, with claims of better theoretical convergence rates and practical advantages over standard Frank-Wolfe methods.

  7. Why Do We Need Warm-up? A Theoretical Perspective

    cs.LG 2025-10 conditional novelty 5.0

    Under the proposed (H0,H1)-smoothness condition, gradient descent with a warm-up-style adaptive step-size provably converges faster than with any fixed step-size.