Functional Gradient Descent with Adaptive Representations

• URL: http://arxiv.org/abs/2606.16926v1
• Date: Mon, 15 Jun 2026 16:27:25 GMT
• Title: Functional Gradient Descent with Adaptive Representations
• Abstract summary: We propose a new, theoretically-grounded functional descent (FGD) algorithm for functional optimization problems.<n>FGD is difficult to implement in practice because functional gradients cannot be fully computed nor stored in memory.<n>We show that our algorithm consistently outperforms both FGD with fixed approximations and neural network baselines in efficiency accuracy.
• Score: 6.479603810066888
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Functional optimization problems are typically solved by optimizing the parameters of a fixed representation, such as a neural network, resulting in highly nonconvex losses that complicate both training and theoretical analysis. An interesting alternative is functional gradient descent (FGD), that is, gradient descent directly in function space, which benefits from strong convergence results and admits a clean theory. However, FGD is difficult to implement in practice because functional gradients are infinite-dimensional, and thus cannot be fully computed nor stored in memory. Existing implementations therefore rely on fixed approximations, which introduce approximation error. We propose a new, theoretically-grounded FGD algorithm that adapts the representation of the functional gradients over the course of optimization. By explicitly incorporating this approximation into the analysis, we establish convergence to a stationary point (for smooth losses) and to a global minimizer (under smoothness + a Polyak-Lojasiewicz-type condition) regardless of our approximations. To the best of our knowledge, this is the first implementable FGD method with such guarantees in a general setting. We demonstrate the effectiveness of our method on regression, numerical solution of PDEs, and modern computer vision. Across settings, our method consistently outperforms both FGD with fixed approximations and neural network baselines in efficiency and accuracy.

Related papers

• A Parameter-Free First-Order Algorithm for Non-Convex Optimization with $\tilde{\mkern1mu O}(ε^{-5/3})$ Global Rate [0.12744523252873352]
  We introduce PF-AGD, the first parameter-free, accelerated first-order method to achieve $O(-5)$ complexity on smooth non-log objectives.
  arXiv  Detail & Related papers  (2026-05-04T01:17:06Z)
• An Efficient Spatial Branch-and-Bound Algorithm for Global Optimization of Gaussian Process Posterior Mean Functions [2.738648582869357]
  We show that a piecewise-analytic lower-boundangular representation in reduced-space spatial branch-and-bound yields a valid for the mean.<n>Results show that PALM-Mean improves on representative general-purpose global training as the number of data points increases.
  arXiv  Detail & Related papers  (2026-04-21T01:13:54Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• How Does Adaptive Optimization Impact Local Neural Network Geometry? [32.32593743852949]
  We argue that in the context of neural network optimization, this traditional viewpoint is insufficient. We show that adaptive methods such as Adam bias the trajectories towards regions where one might expect faster convergence.
  arXiv  Detail & Related papers  (2022-11-04T04:05:57Z)
• The computational asymptotics of Gaussian variational inference and the Laplace approximation [19.366538729532856]
  We provide a theoretical analysis of the convexity properties of variational inference with a Gaussian family. We show that with scaled real-data examples both CSVI and CSV improve the likelihood of obtaining the global optimum of their respective optimization problems.
  arXiv  Detail & Related papers  (2021-04-13T01:23:34Z)
• Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework [100.36569795440889]
  This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information. We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
  arXiv  Detail & Related papers  (2020-12-21T17:29:58Z)
• An adaptive stochastic gradient-free approach for high-dimensional blackbox optimization [0.0]
  We propose an adaptive gradient-free (ASGF) approach for high-dimensional non-smoothing problems. We illustrate the performance of this method on benchmark global problems and learning tasks.
  arXiv  Detail & Related papers  (2020-06-18T22:47:58Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)
• 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)
• On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization [80.03647903934723]
  We prove adaptive gradient methods in expectation of gradient convergence methods. Our analyses shed light on better adaptive gradient methods in optimizing non understanding gradient bounds.
  arXiv  Detail & Related papers  (2018-08-16T20:25:28Z)

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.