Efficient Bilevel Optimization with KFAC-Based Hypergradients

• URL: http://arxiv.org/abs/2603.29108v1
• Date: Tue, 31 Mar 2026 00:54:31 GMT
• Title: Efficient Bilevel Optimization with KFAC-Based Hypergradients
• Abstract summary: Bilevel optimization (BO) is widely applicable to many machine learning problems.<n>We build on implicit function theorem-based algorithms and propose to incorporate Kronecker-factored approximate curvature (KFAC)<n>KFAC yields curvature-aware hypergradients with a better performance efficiency trade-off than Conjugate Gradient (CG) or Neumann methods.
• Score: 31.485951578283277
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bilevel optimization (BO) is widely applicable to many machine learning problems. Scaling BO, however, requires repeatedly computing hypergradients, which involves solving inverse Hessian-vector products (IHVPs). In practice, these operations are often approximated using crude surrogates such as one-step gradient unrolling or identity/short Neumann expansions, which discard curvature information. We build on implicit function theorem-based algorithms and propose to incorporate Kronecker-factored approximate curvature (KFAC), yielding curvature-aware hypergradients with a better performance efficiency trade-off than Conjugate Gradient (CG) or Neumann methods and consistently outperforming unrolling. We evaluate this approach across diverse tasks, including meta-learning and AI safety problems. On models up to BERT, we show that curvature information is valuable at scale, and KFAC can provide it with only modest memory and runtime overhead. Our implementation is available at https://github.com/liaodisen/NeuralBo.

Related papers

• When Bayesian Tensor Completion Meets Multioutput Gaussian Processes: Functional Universality and Rank Learning [53.17227599983122]
  Functional tensor decomposition can analyze multi-dimensional data with real-valued indices.<n>We propose a rank-revealing functional low-rank tensor completion (RR-F) method.<n>We establish the universal approximation property of the model for continuous multi-dimensional signals.
  arXiv  Detail & Related papers  (2025-12-25T03:15:52Z)
• Bilevel Learning via Inexact Stochastic Gradient Descent [5.312803257246881]
  Bilevel optimization is a central tool in machine learning for high-dimensional hyper tuning.<n>We advance the theory of inexact bilevel optimization.<n>We prove convergence and establish rates under decaying accuracy and step size schedules.
  arXiv  Detail & Related papers  (2025-11-10T07:02:52Z)
• Linearly Convergent Mixup Learning [0.0]
  We present two novel algorithms that extend to a broader range of binary classification models.<n>Unlike gradient-based approaches, our algorithms do not require hyper parameters like learning rates, simplifying their implementation and optimization.<n>Our algorithms achieve faster convergence to the optimal solution compared to descent gradient approaches, and that mixup data augmentation consistently improves the predictive performance across various loss functions.
  arXiv  Detail & Related papers  (2025-01-14T02:33:40Z)
• A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning [74.80956524812714]
  We tackle the general differentiable meta learning problem that is ubiquitous in modern deep learning. These problems are often formalized as Bi-Level optimizations (BLO) We introduce a novel perspective by turning a given BLO problem into a ii optimization, where the inner loss function becomes a smooth distribution, and the outer loss becomes an expected loss over the inner distribution.
  arXiv  Detail & Related papers  (2024-10-14T12:10:06Z)
• Equation Discovery with Bayesian Spike-and-Slab Priors and Efficient Kernels [57.46832672991433]
  We propose a novel equation discovery method based on Kernel learning and BAyesian Spike-and-Slab priors (KBASS) We use kernel regression to estimate the target function, which is flexible, expressive, and more robust to data sparsity and noises. We develop an expectation-propagation expectation-maximization algorithm for efficient posterior inference and function estimation.
  arXiv  Detail & Related papers  (2023-10-09T03:55:09Z)
• Non-Convex Bilevel Optimization with Time-Varying Objective Functions [57.299128109226025]
  We propose an online bilevel optimization where the functions can be time-varying and the agent continuously updates the decisions with online data. Compared to existing algorithms, SOBOW is computationally efficient and does not need to know previous functions. We show that SOBOW can achieve a sublinear bilevel local regret under mild conditions.
  arXiv  Detail & Related papers  (2023-08-07T06:27:57Z)
• BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach [46.457298683984924]
  Bilevel optimization (BO) is useful for solving a variety important machine learning problems. Conventional methods need to differentiate through the low-level optimization process with implicit differentiation. First-order BO depends only on first-order information, requires no implicit differentiation.
  arXiv  Detail & Related papers  (2022-09-19T01:51:12Z)
• Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems [0.0]
  Two-level formula search optimization has become instrumental in a number of machine learning contexts. New low-rank bi-level gradient methods are developed that do not require second-order derivatives.
  arXiv  Detail & Related papers  (2021-10-01T18:20:14Z)
• Explicit Gradient Learning [28.844181847562695]
  Black-Box Optimization (BBO) methods can find optimal systems with no analytical representation. EGL trains a NN to estimate the objective gradient directly.
  arXiv  Detail & Related papers  (2020-06-09T08:56:24Z)
• Global Optimization of Gaussian processes [52.77024349608834]
  We propose a reduced-space formulation with trained Gaussian processes trained on few data points. The approach also leads to significantly smaller and computationally cheaper sub solver for lower bounding. In total, we reduce time convergence by orders of orders of the proposed method.
  arXiv  Detail & Related papers  (2020-05-21T20:59:11Z)
• 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.