An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness

• URL: http://arxiv.org/abs/2409.19212v2
• Date: Wed, 30 Oct 2024 19:05:17 GMT
• Title: An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
• Authors: Xiaochuan Gong, Jie Hao, Mingrui Liu,
• Abstract summary: This paper investigates a class of bilevel optimization problems where the upper-level function is non- unbounded smoothness and the lower-level problem is strongly convex. These problems have significant applications in data learning, such as text classification using neural networks.
• Score: 15.656614304616006
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper investigates a class of stochastic bilevel optimization problems where the upper-level function is nonconvex with potentially unbounded smoothness and the lower-level problem is strongly convex. These problems have significant applications in sequential data learning, such as text classification using recurrent neural networks. The unbounded smoothness is characterized by the smoothness constant of the upper-level function scaling linearly with the gradient norm, lacking a uniform upper bound. Existing state-of-the-art algorithms require $\widetilde{O}(1/\epsilon^4)$ oracle calls of stochastic gradient or Hessian/Jacobian-vector product to find an $\epsilon$-stationary point. However, it remains unclear if we can further improve the convergence rate when the assumptions for the function in the population level also hold for each random realization almost surely (e.g., Lipschitzness of each realization of the stochastic gradient). To address this issue, we propose a new Accelerated Bilevel Optimization algorithm named AccBO. The algorithm updates the upper-level variable by normalized stochastic gradient descent with recursive momentum and the lower-level variable by the stochastic Nesterov accelerated gradient descent algorithm with averaging. We prove that our algorithm achieves an oracle complexity of $\widetilde{O}(1/\epsilon^3)$ to find an $\epsilon$-stationary point. Our proof relies on a novel lemma characterizing the dynamics of stochastic Nesterov accelerated gradient descent algorithm under distribution drift with high probability for the lower-level variable, which is of independent interest and also plays a crucial role in analyzing the hypergradient estimation error over time. Experimental results on various tasks confirm that our proposed algorithm achieves the predicted theoretical acceleration and significantly outperforms baselines in bilevel optimization.

Related papers

• Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity [59.75300530380427]
  We consider the problem of optimizing second-order smooth and strongly convex functions where the algorithm is only accessible to noisy evaluations of the objective function it queries. We provide the first tight characterization for the rate of the minimax simple regret by developing matching upper and lower bounds.
  arXiv  Detail & Related papers  (2024-06-28T02:56:22Z)
• Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis [17.596465452814883]
  Current bilevel optimization algorithms assume that the iterations of the upper-level function is unbounded smooth. Recent studies reveal that certain neural networks exhibit such unbounded smoothness.
  arXiv  Detail & Related papers  (2024-01-17T20:28:15Z)
• Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions [9.518010235273785]
  We present a novel fully Liploop Hessian-inversion-free algorithmic framework for bilevel optimization. We show that by a slight modification of our approach our approach can handle a more general multi-objective robust bilevel optimization problem.
  arXiv  Detail & Related papers  (2023-06-21T07:32:29Z)
• Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization [116.89941263390769]
  We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $min_mathbfxmax_mathbfyF(mathbfx) + H(mathbfx,mathbfy)$, where one has access to first-order oracles for $F$, $G$ as well as the bilinear coupling function $H$. We present a emphaccelerated gradient-extragradient (AG-EG) descent-ascent algorithm that combines extragrad
  arXiv  Detail & Related papers  (2022-06-17T06:10:20Z)
• A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization [26.68351521813062]
  Existing bi-level algorithms cannot handle nonsmooth or hyper-smooth regularizers. In this paper, we show that an implicit differentiation (AID) scheme can be used to speed up comprehensive machine learning applications.
  arXiv  Detail & Related papers  (2022-03-30T18:53:04Z)
• Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization [50.83356836818667]
  gradient Langevin Dynamics is one of the most fundamental algorithms to solve non-eps optimization problems. In this paper, we show two variants of this kind, namely the Variance Reduced Langevin Dynamics and the Recursive Gradient Langevin Dynamics.
  arXiv  Detail & Related papers  (2022-03-30T11:39:00Z)
• Efficiently Escaping Saddle Points in Bilevel Optimization [48.925688192913]
  Bilevel optimization is one of the problems in machine learning. Recent developments in bilevel optimization converge on the first fundamental nonaptature multi-step analysis.
  arXiv  Detail & Related papers  (2022-02-08T07:10:06Z)
• A Momentum-Assisted Single-Timescale Stochastic Approximation Algorithm for Bilevel Optimization [112.59170319105971]
  We propose a new algorithm -- the Momentum- Single-timescale Approximation (MSTSA) -- for tackling problems. MSTSA allows us to control the error in iterations due to inaccurate solution to the lower level subproblem.
  arXiv  Detail & Related papers  (2021-02-15T07:10:33Z)
• Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets [71.05306664267832]
  Adaptive algorithms perform gradient updates using the history of gradients and are ubiquitous in training deep neural networks. In this paper we analyze a variant of OptimisticOA algorithm for nonconcave minmax problems. Our experiments show that adaptive GAN non-adaptive gradient algorithms can be observed empirically.
  arXiv  Detail & Related papers  (2019-12-26T22:10:10Z)

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.