Gradient Descent's Last Iterate is Often (slightly) Suboptimal

• URL: http://arxiv.org/abs/2604.13870v1
• Date: Wed, 15 Apr 2026 13:33:08 GMT
• Title: Gradient Descent's Last Iterate is Often (slightly) Suboptimal
• Abstract summary: We consider the setting of minimizing a convex Lipschitz function using either gradient descent (GD) or its optimal variant (SGD)<n>We show that even in the noiseless case of GD, it is impossible to avoid an excess poly-log factor in $T$ when considering an anytime last iterate guarantee.
• Score: 30.492009313545257
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the well-studied setting of minimizing a convex Lipschitz function using either gradient descent (GD) or its stochastic variant (SGD), and examine the last iterate convergence. By now, it is known that standard stepsize choices lead to a last iterate convergence rate of $\log T/\sqrt{T}$ after $T$ steps. A breakthrough result of Jain et al. [2019] recovered the optimal $1/\sqrt{T}$ rate by constructing a non-standard stepsize sequence. However, this sequence requires choosing $T$ in advance, as opposed to common stepsize schedules which apply for any time horizon. Moreover, Jain et al. conjectured that without prior knowledge of $T$, no stepsize sequence can ensure the optimal error for SGD's last iterate, a claim which so far remained unproven. We prove this conjecture, and in fact show that even in the noiseless case of GD, it is impossible to avoid an excess poly-log factor in $T$ when considering an anytime last iterate guarantee. Our proof further suggests that such (slightly) suboptimal stopping times are unavoidably common.

Related papers

• New Bounds for the Last Iterate of the Stochastic subGradient Method [11.179752660122281]
  We study the last iterate of the subgradient method for one-dimensional convex Lipschitz objectives.<n>Under additive i.i.d. subgradient noise with uniformly bounded variance, the last iterate features an optimization error of order $1/sqrt n$.<n>We show that without the i.i.d. assumption, the optimization error can be of order $(log n)/sqrt n$.
  arXiv  Detail & Related papers  (2026-06-23T17:55:18Z)
• Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences [51.56484100374058]
  We study stopping rules for gradient descent (SGD) for convex optimization.<n>We develop an anytime-valid, data-dependent upper confidence sequence for the weighted average suboptimality of projected SGD.<n>These are the first rigorous, time-uniform performance guarantees and finitetime $varepsilon$-optimality certificates.
  arXiv  Detail & Related papers  (2025-12-15T09:26:45Z)
• Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime [26.711510824243803]
  We study population convergence guarantees of gradient descent (SGD) for smooth convex objectives in the regime, where the noise at optimum is zero or near zero.<n>For a well-tuned stepsize we obtain a near optimal $widetildeO (1/T + sigma_star/sqrtT)$ rate for the last iterate.
  arXiv  Detail & Related papers  (2025-07-15T12:52:47Z)
• From Continual Learning to SGD and Back: Better Rates for Continual Linear Models [50.11453013647086]
  We analyze the forgetting, i.e., loss on previously seen tasks, after $k$ iterations.<n>We develop novel last-iterate upper bounds in the realizable least squares setup.<n>We prove for the first time that randomization alone, with no task repetition, can prevent catastrophic in sufficiently long task sequences.
  arXiv  Detail & Related papers  (2025-04-06T18:39:45Z)
• Anytime Acceleration of Gradient Descent [92.02082223856479]
  We investigate stepsize-based acceleration of gradient descent with em anytime convergence guarantees.<n>For smooth (non-strongly) convex optimization, we propose a stepsize schedule that allows gradient descent to achieve convergence guarantees of $O(T-1.119)$ for any stopping time.
  arXiv  Detail & Related papers  (2024-11-26T18:29:44Z)
• Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods [25.831462008050387]
  The Gradient Descent (SGD) algorithm has triggered people's interest due to its good performance in practice but lack of theoretical understanding. It still remains unclear whether the lastiterate convergence can be provably extended to wider composite optimization and non-Euclidean norms.
  arXiv  Detail & Related papers  (2023-12-13T21:41:06Z)
• Non-stationary Delayed Online Convex Optimization: From Full-information to Bandit Setting [71.82716109461967]
  We propose an algorithm called Mild-OGD for the full-information case, where delayed gradients are available.<n>We show that the dynamic regret of Mild-OGD can be automatically bounded by $O(sqrtbardT(P_T+1))$ under the in-order assumption.<n>We also develop a bandit variant of Mild-OGD for a more challenging case with only delayed loss values.
  arXiv  Detail & Related papers  (2023-05-20T07:54:07Z)
• Optimal and instance-dependent guarantees for Markovian linear stochastic approximation [47.912511426974376]
  We show a non-asymptotic bound of the order $t_mathrmmix tfracdn$ on the squared error of the last iterate of a standard scheme. We derive corollaries of these results for policy evaluation with Markov noise.
  arXiv  Detail & Related papers  (2021-12-23T18:47:50Z)
• The Convergence Rate of SGD's Final Iterate: Analysis on Dimension Dependence [2.512827436728378]
  Gradient Descent (SGD) is among the simplest and most popular methods in optimization. We show how to characterize the final-iterate convergence of SGD in the constant dimension setting.
  arXiv  Detail & Related papers  (2021-06-28T11:51:04Z)
• ROOT-SGD: Sharp Nonasymptotics and Near-Optimal Asymptotics in a Single Algorithm [71.13558000599839]
  We study the problem of solving strongly convex and smooth unconstrained optimization problems using first-order algorithms. We devise a novel, referred to as Recursive One-Over-T SGD, based on an easily implementable, averaging of past gradients. We prove that it simultaneously achieves state-of-the-art performance in both a finite-sample, nonasymptotic sense and an sense.
  arXiv  Detail & Related papers  (2020-08-28T14:46:56Z)
• On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems [75.58134963501094]
  This paper analyzes the trajectories of gradient descent (SGD) We show that SGD avoids saddle points/manifolds with $1$ for strict step-size policies.
  arXiv  Detail & Related papers  (2020-06-19T14:11:26Z)

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.