Parameter Tuning with Generalization Guarantees for GPU-Accelerated Linear Programming

• URL: http://arxiv.org/abs/2606.08638v1
• Date: Sun, 07 Jun 2026 14:01:42 GMT
• Title: Parameter Tuning with Generalization Guarantees for GPU-Accelerated Linear Programming
• Abstract summary: We derive generalization guarantees for hyperparameter tuning within (cu)PDLP, a state-of-the-art first-order LP solver designed for modern hardware.<n>First, we pin down the behavior of PDHG, the primal-dual hybrid gradient algorithm that underlies PDLP, as a function of its step size and primal weight.<n>We then conduct a structural analysis of PDLP, which augments PDHG with several specialized techniques like preconditioning, adaptive step sizes, averaging, restarts, and smoothed primal weight updates.
• Score: 16.092527463250708
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent research has developed practical, parallelizable first-order methods for large scale linear programming, but performance is highly dependent on hyperparameter selection. We derive generalization guarantees for hyperparameter tuning within (cu)PDLP, a state-of-the-art first-order LP solver designed for modern hardware. First, we pin down the behavior of PDHG, the primal-dual hybrid gradient algorithm that underlies PDLP, as a function of its step size and primal weight, leading to linear sample complexity guarantees for learning those parameters. We then conduct a structural analysis of PDLP, which augments PDHG with several specialized techniques like preconditioning, adaptive step sizes, averaging, adaptive restarts, and smoothed primal weight updates. Our analysis captures the behavior of the solution trajectory as a function of the hyperparameters and leverages recent advances in data-driven algorithm design to obtain polynomial sample complexity guarantees for learning those hyperparameters. Finally, we conduct proof-of-concept experiments that demonstrate the need for data-driven PDLP parameter tuning. Our results showcase the versatility of the data-driven algorithm design toolkit for principled hyperparameter tuning within solver-grade implementations of complex modern optimization algorithms.

Related papers

• New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework [52.69678300445233]
  Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or.<n>Efficient Fine-Tuning (PEFT) adjusts a small subset of parameters.<n>We propose a novel hybrid fine-tuning approach that jointly updates both LLMs and PEFT modules using a combination of zeroth-order and first-order optimization methods.
  arXiv  Detail & Related papers  (2026-04-10T22:39:38Z)
• Parallel Diffusion Solver via Residual Dirichlet Policy Optimization [88.7827307535107]
  Diffusion models (DMs) have achieved state-of-the-art generative performance but suffer from high sampling latency due to their sequential denoising nature.<n>Existing solver-based acceleration methods often face significant image quality degradation under a low-dimensional budget.<n>We propose the Ensemble Parallel Direction solver (dubbed as EPD-EPr), a novel ODE solver that mitigates these errors by incorporating multiple gradient parallel evaluations in each step.
  arXiv  Detail & Related papers  (2025-12-28T05:48:55Z)
• Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations [50.010924231754856]
  Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence.<n>To overcome this, parameter-efficient fine-tuning (PEFT) methods like LoRA have emerged and are becoming a growing research focus.<n>We propose a generalization that extends matrix-based PEFT methods to higher-dimensional parameter spaces without compromising their structural properties.
  arXiv  Detail & Related papers  (2025-04-01T14:36:45Z)
• Optimal DLT-based Solutions for the Perspective-n-Point [0.0]
  We propose a modified direct linear (DLT) algorithm for solving the perspective-n-point (Newton)<n>The modification consists analytically weighting the different measurements in the linear system with a negligible increase in computational load.<n>Our approach clears improvements in both performance and runtime.
  arXiv  Detail & Related papers  (2024-10-18T04:04:58Z)
• Sparse high-dimensional linear regression with a partitioned empirical Bayes ECM algorithm [62.997667081978825]
  We propose a computationally efficient and powerful Bayesian approach for sparse high-dimensional linear regression. Minimal prior assumptions on the parameters are used through the use of plug-in empirical Bayes estimates. The proposed approach is implemented in the R package probe.
  arXiv  Detail & Related papers  (2022-09-16T19:15:50Z)
• Towards Learning Universal Hyperparameter Optimizers with Transformers [57.35920571605559]
  We introduce the OptFormer, the first text-based Transformer HPO framework that provides a universal end-to-end interface for jointly learning policy and function prediction. Our experiments demonstrate that the OptFormer can imitate at least 7 different HPO algorithms, which can be further improved via its function uncertainty estimates.
  arXiv  Detail & Related papers  (2022-05-26T12:51:32Z)
• Accelerated nonlinear primal-dual hybrid gradient algorithms with applications to machine learning [0.0]
  primal-dual hybrid gradient (PDHG) is a first-order method that splits convex optimization problems with saddle-point structure into smaller subproblems. PDHG requires stepsize parameters fine-tuned for the problem at hand. We introduce accelerated nonlinear variants of the PDHG algorithm that can achieve, for a broad class of optimization problems relevant to machine learning.
  arXiv  Detail & Related papers  (2021-09-24T22:37:10Z)
• Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling [0.9806910643086042]
  We develop a new method of online inference for a vector of parameters estimated by the Polyak-Rtupper averaging procedure of gradient descent algorithms. Our approach is fully operational with online data and is rigorously underpinned by a functional central limit theorem.
  arXiv  Detail & Related papers  (2021-06-06T15:38:37Z)
• Adaptive pruning-based optimization of parameterized quantum circuits [62.997667081978825]
  Variisy hybrid quantum-classical algorithms are powerful tools to maximize the use of Noisy Intermediate Scale Quantum devices. We propose a strategy for such ansatze used in variational quantum algorithms, which we call "Efficient Circuit Training" (PECT) Instead of optimizing all of the ansatz parameters at once, PECT launches a sequence of variational algorithms.
  arXiv  Detail & Related papers  (2020-10-01T18:14:11Z)
• Objective-Sensitive Principal Component Analysis for High-Dimensional Inverse Problems [0.0]
  We present a novel approach for adaptive, differentiable parameterization of large-scale random fields. The developed technique is based on principal component analysis (PCA) but modifies a purely data-driven basis of principal components considering objective function behavior. Three algorithms for optimal parameter decomposition are presented and applied to an objective of 2D synthetic history matching.
  arXiv  Detail & Related papers  (2020-06-02T18:51:17Z)

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.