Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness

• URL: http://arxiv.org/abs/2505.04599v1
• Date: Wed, 07 May 2025 17:40:12 GMT
• Title: Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness
• Authors: Michael Crawshaw, Mingrui Liu,
• Abstract summary: Recent results in non-stationary optimization demonstrate the convergence of popular adaptive algorithms.<n> complexity of convergence is a higher-order in terms of problem parameters like smoothness constants.
• Score: 14.98493572536424
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent results in non-convex stochastic optimization demonstrate the convergence of popular adaptive algorithms (e.g., AdaGrad) under the $(L_0, L_1)$-smoothness condition, but the rate of convergence is a higher-order polynomial in terms of problem parameters like the smoothness constants. The complexity guaranteed by such algorithms to find an $\epsilon$-stationary point may be significantly larger than the optimal complexity of $\Theta \left( \Delta L \sigma^2 \epsilon^{-4} \right)$ achieved by SGD in the $L$-smooth setting, where $\Delta$ is the initial optimality gap, $\sigma^2$ is the variance of stochastic gradient. However, it is currently not known whether these higher-order dependencies can be tightened. To answer this question, we investigate complexity lower bounds for several adaptive optimization algorithms in the $(L_0, L_1)$-smooth setting, with a focus on the dependence in terms of problem parameters $\Delta, L_0, L_1$. We provide complexity bounds for three variations of AdaGrad, which show at least a quadratic dependence on problem parameters $\Delta, L_0, L_1$. Notably, we show that the decorrelated variant of AdaGrad-Norm requires at least $\Omega \left( \Delta^2 L_1^2 \sigma^2 \epsilon^{-4} \right)$ stochastic gradient queries to find an $\epsilon$-stationary point. We also provide a lower bound for SGD with a broad class of adaptive stepsizes. Our results show that, for certain adaptive algorithms, the $(L_0, L_1)$-smooth setting is fundamentally more difficult than the standard smooth setting, in terms of the initial optimality gap and the smoothness constants.

Related papers

• Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum [30.01198677588252]
  First-order algorithms require at least $mathcalO(varepsilonepsilon-4)$ complexity to find an $varepsilon-stationary point.<n>We introduce novel momentum algorithms utilizing efficient variable complexity.<n>The effectiveness of the method is validated through robust logistic regression using real-world datasets.
  arXiv  Detail & Related papers  (2024-06-18T20:14:52Z)
• An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization [37.300102993926046]
  We study the complexity of producing neither smooth nor convex points of Lipschitz objectives which are possibly using only zero-order evaluations. Our analysis is based on a simple yet powerful. Goldstein-subdifferential set, which allows recent advancements in. nonsmooth non optimization.
  arXiv  Detail & Related papers  (2023-07-10T11:56:04Z)
• An Oblivious Stochastic Composite Optimization Algorithm for Eigenvalue Optimization Problems [76.2042837251496]
  We introduce two oblivious mirror descent algorithms based on a complementary composite setting. Remarkably, both algorithms work without prior knowledge of the Lipschitz constant or smoothness of the objective function. We show how to extend our framework to scale and demonstrate the efficiency and robustness of our methods on large scale semidefinite programs.
  arXiv  Detail & Related papers  (2023-06-30T08:34:29Z)
• ReSQueing Parallel and Private Stochastic Convex Optimization [59.53297063174519]
  We introduce a new tool for BFG convex optimization (SCO): a Reweighted Query (ReSQue) estimator for the gradient of a function convolved with a (Gaussian) probability density. We develop algorithms achieving state-of-the-art complexities for SCO in parallel and private settings.
  arXiv  Detail & Related papers  (2023-01-01T18:51:29Z)
• Best Policy Identification in Linear MDPs [70.57916977441262]
  We investigate the problem of best identification in discounted linear Markov+Delta Decision in the fixed confidence setting under a generative model. The lower bound as the solution of an intricate non- optimization program can be used as the starting point to devise such algorithms.
  arXiv  Detail & Related papers  (2022-08-11T04:12:50Z)
• Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity [121.83085611327654]
  We structured convex optimization problems with additive objective $r:=p + q$, where $r$ is $mu$-strong convex similarity. We proposed a method to solve problems master to agents' communication and local calls. The proposed method is much sharper than the $mathcalO(sqrtL_q/mu)$ method.
  arXiv  Detail & Related papers  (2022-05-30T14:28:02Z)
• Optimal Algorithms for Stochastic Multi-Level Compositional Optimization [46.77664277596764]
  We solve the problem of multi-level compositional optimization, where the objective function is a limitation of multiple but possibly non-optimal functions. To make use of the Adaptive Multi-level Variance Reduction method (SMVR), we also achieves the same optimal complexities but converges faster in practice.
  arXiv  Detail & Related papers  (2022-02-15T16:02:32Z)
• A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization [12.096252285460814]
  We propose a projection-free conditional gradient-type algorithm for composition optimization. We show that the number of oracles and the linear-minimization oracle required by the proposed algorithm, are of order $mathcalO_T(epsilon-2)$ and $mathcalO_T(epsilon-3)$ respectively.
  arXiv  Detail & Related papers  (2022-02-09T06:05:38Z)
• Oracle Complexity in Nonsmooth Nonconvex Optimization [49.088972349825085]
  It is well-known that given a smooth, bounded-from-below $$stationary points, Oracle-based methods can find smooth approximation of smoothness. In this paper, we prove an inherent trade-off between optimization and smoothing dimension.
  arXiv  Detail & Related papers  (2021-04-14T10:42:45Z)
• The Complexity of Nonconvex-Strongly-Concave Minimax Optimization [43.07732143522183]
  This paper establishes the complexity for finding approximate stationary points of non-strongly-concave (NC-SC) smooth minimax problems. We deploy a proposed sequence of $Omega-strong$lyconcave sub-2 problems in both general complexity and averaged complexity. In our proposed finite-sum setting, our proposed algorithm provides a nearly-tight dependence on the condition number.
  arXiv  Detail & Related papers  (2021-03-29T18:53:57Z)
• A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic [142.1492359556374]
  Bilevel optimization is a class of problems which exhibit a two-level structure. We propose a two-timescale approximation (TTSA) algorithm for tackling such a bilevel problem. We show that a two-timescale natural actor-critic policy optimization algorithm can be viewed as a special case of our TTSA framework.
  arXiv  Detail & Related papers  (2020-07-10T05:20:02Z)
• Gradient Free Minimax Optimization: Variance Reduction and Faster Convergence [120.9336529957224]
  In this paper, we denote the non-strongly setting on the magnitude of a gradient-free minimax optimization problem. We show that a novel zeroth-order variance reduced descent algorithm achieves the best known query complexity.
  arXiv  Detail & Related papers  (2020-06-16T17:55:46Z)

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.