Convergence Rate Analysis of LION

• URL: http://arxiv.org/abs/2411.07724v1
• Date: Tue, 12 Nov 2024 11:30:53 GMT
• Title: Convergence Rate Analysis of LION
• Authors: Yiming Dong, Huan Li, Zhouchen Lin,
• Abstract summary: LION converges iterations of $cal(sqrtdK-)$ measured by gradient Karush-Kuhn-T (sqrtdK-)$. We show that LION can achieve lower loss and higher performance compared to standard SGD.
• Score: 54.28350823319057
• License:
• Abstract: The LION (evoLved sIgn mOmeNtum) optimizer for deep neural network training was found by Google via program search, with the simple sign update yet showing impressive performance in training large scale networks. Although previous studies have investigated its convergence properties, a comprehensive analysis, especially the convergence rate, is still desirable. Recognizing that LION can be regarded as solving a specific constrained problem, this paper focuses on demonstrating its convergence to the Karush-Kuhn-Tucker (KKT) point at the rate of $\cal O(\sqrt{d}K^{-1/4})$ measured by gradient $\ell_1$ norm, where $d$ is the problem dimension and $K$ is the number of iteration steps. Step further, we remove the constraint and establish that LION converges to the critical point of the general unconstrained problem at the same rate. This rate not only delivers the currently optimal dependence on the problem dimension $d$ but also tightly matches the theoretical lower bound for nonconvex stochastic optimization algorithms, which is typically measured using the gradient $\ell_2$ norm, with respect to the number of iterations $K$. Through extensive experiments, we not only demonstrate that LION achieves lower loss and higher performance compared to standard SGD, but also empirically confirm that the gradient $\ell_1/\ell_2$ norm ratio aligns with $\Theta(\sqrt{d})$, thus proving that our convergence rate matches the theoretical lower bound with respect to $d$ in the empirical sense.

Related papers

• Matching the Statistical Query Lower Bound for k-sparse Parity Problems with Stochastic Gradient Descent [83.85536329832722]
  We show that gradient descent (SGD) can efficiently solve the $k$-parity problem on a $d$dimensional hypercube. We then demonstrate how a trained neural network with SGD, solving the $k$-parity problem with small statistical errors.
  arXiv  Detail & Related papers  (2024-04-18T17:57:53Z)
• Analysis of the expected $L_2$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization [7.977229957867868]
  Recent results show that estimates defined by over-parametrized deep neural networks learned by applying gradient descent to a regularized empirical $L$ risk are universally consistent. In this paper, we show that the regularization term is not necessary to obtain similar results.
  arXiv  Detail & Related papers  (2023-11-24T17:04:21Z)
• Adaptive, Doubly Optimal No-Regret Learning in Strongly Monotone and Exp-Concave Games with Gradient Feedback [75.29048190099523]
  Online gradient descent (OGD) is well known to be doubly optimal under strong convexity or monotonicity assumptions. In this paper, we design a fully adaptive OGD algorithm, textsfAdaOGD, that does not require a priori knowledge of these parameters.
  arXiv  Detail & Related papers  (2023-10-21T18:38:13Z)
• Empirical Risk Minimization with Shuffled SGD: A Primal-Dual Perspective and Improved Bounds [12.699376765058137]
  gradient descent (SGD) is perhaps the most prevalent optimization method in modern machine learning. It is only very recently that SGD with sampling without replacement -- shuffled SGD -- has been analyzed. We prove fine-grained complexity bounds that depend on the data matrix and are never worse than what is predicted by the existing bounds.
  arXiv  Detail & Related papers  (2023-06-21T18:14:44Z)
• Restricted Strong Convexity of Deep Learning Models with Smooth Activations [31.003601717265006]
  We study the problem of optimization of deep learning models with smooth activation functions. We introduce a new analysis of optimization based on Restricted Strong Convexity (RSC) Ours is the first result on establishing geometric convergence of GD based on RSC for deep learning models.
  arXiv  Detail & Related papers  (2022-09-29T21:24:26Z)
• Provably Efficient Convergence of Primal-Dual Actor-Critic with Nonlinear Function Approximation [15.319335698574932]
  We show the first efficient convergence result with primal-dual actor-critic with a convergence of $mathcalOleft ascent(Nright)Nright)$ under Polyian sampling. Results on Open GymAI continuous control tasks.
  arXiv  Detail & Related papers  (2022-02-28T15:16:23Z)
• An efficient projection neural network for $\ell_1$-regularized logistic regression [10.517079029721257]
  This paper presents a simple projection neural network for $ell_$-regularized logistics regression. The proposed neural network does not require any extra auxiliary variable nor any smooth approximation. We also investigate the convergence of the proposed neural network by using the Lyapunov theory and show that it converges to a solution of the problem with any arbitrary initial value.
  arXiv  Detail & Related papers  (2021-05-12T06:13:44Z)
• Fast Rates for the Regret of Offline Reinforcement Learning [69.23654172273085]
  We study the regret of reinforcement learning from offline data generated by a fixed behavior policy in an infinitehorizon discounted decision process (MDP) We show that given any estimate for the optimal quality function $Q*$, the regret of the policy it defines converges at a rate given by the exponentiation of the $Q*$-estimate's pointwise convergence rate.
  arXiv  Detail & Related papers  (2021-01-31T16:17:56Z)
• Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave Sampling [110.88857917726276]
  We provide a new convergence analysis of gradient Langevin dynamics (SGLD) for sampling from a class of distributions that can be non-log-concave. At the core of our approach is a novel conductance analysis of SGLD using an auxiliary time-reversible Markov Chain.
  arXiv  Detail & Related papers  (2020-10-19T15:23:18Z)
• A Simple Convergence Proof of Adam and Adagrad [74.24716715922759]
  We show a proof of convergence between the Adam Adagrad and $O(d(N)/st)$ algorithms. Adam converges with the same convergence $O(d(N)/st)$ when used with the default parameters.
  arXiv  Detail & Related papers  (2020-03-05T01:56:17Z)

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.