Towards Robust Learning to Optimize with Theoretical Guarantees

• URL: http://arxiv.org/abs/2506.14263v1
• Date: Tue, 17 Jun 2025 07:25:07 GMT
• Title: Towards Robust Learning to Optimize with Theoretical Guarantees
• Authors: Qingyu Song, Wei Lin, Juncheng Wang, Hong Xu,
• Abstract summary: Learning to optimize (L2O) is an emerging technique to solve mathematical optimization problems with learning-based methods.<n>We show that our proposed model outperforms the state-of-the-art baseline in both InD and OOD scenarios.
• Score: 13.76313767866408
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Learning to optimize (L2O) is an emerging technique to solve mathematical optimization problems with learning-based methods. Although with great success in many real-world scenarios such as wireless communications, computer networks, and electronic design, existing L2O works lack theoretical demonstration of their performance and robustness in out-of-distribution (OOD) scenarios. We address this gap by providing comprehensive proofs. First, we prove a sufficient condition for a robust L2O model with homogeneous convergence rates over all In-Distribution (InD) instances. We assume an L2O model achieves robustness for an InD scenario. Based on our proposed methodology of aligning OOD problems to InD problems, we also demonstrate that the L2O model's convergence rate in OOD scenarios will deteriorate by an equation of the L2O model's input features. Moreover, we propose an L2O model with a concise gradient-only feature construction and a novel gradient-based history modeling method. Numerical simulation demonstrates that our proposed model outperforms the state-of-the-art baseline in both InD and OOD scenarios and achieves up to 10 $\times$ convergence speedup. The code of our method can be found from https://github.com/NetX-lab/GoMathL2O-Official.

Related papers

• SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution [55.14432034345353]
  We study key design principles for latter cascaded video super-resolution models, which are underexplored currently.<n>First, we propose two strategies to generate training pairs that better mimic the output characteristics of the base model, ensuring alignment between the VSR model and its upstream generator.<n>Second, we provide critical insights into VSR model behavior through systematic analysis of (1) timestep sampling strategies, (2) noise augmentation effects on low-resolution (LR) inputs.
  arXiv  Detail & Related papers  (2025-06-24T17:57:26Z)
• Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging [17.038807261969033]
  Long-to-Short (L2S) reasoning aims to balance reasoning depth with practical efficiency.<n>Model merging offers a cost-effective and robust alternative by integrating the quick-thinking capabilities of System 1 models with the methodical reasoning of System 2 models.<n>Our experiments reveal that model merging can reduce average response length by up to 55% while preserving or even improving baseline performance.
  arXiv  Detail & Related papers  (2025-03-26T15:34:37Z)
• Learning Provably Improves the Convergence of Gradient Descent [9.82454981262489]
  We show that L2O lacks theoretical backing for its own convergence highlights.<n>We empirically bridge the gap by proving the convergence of L2O models.<n>We propose a strategy to support theoretical results and promote extended optimization by mitigating gradient explosion.
  arXiv  Detail & Related papers  (2025-01-30T02:03:30Z)
• Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient [57.9629676017527]
  We propose an optimization-based structural pruning on Large-Language Models. We learn the pruning masks in a probabilistic space directly by optimizing the loss of the pruned model. Our method operates for 2.7 hours with around 35GB memory for the 13B models on a single A100 GPU.
  arXiv  Detail & Related papers  (2024-06-15T09:31:03Z)
• Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment [65.15914284008973]
  We propose to leverage an Inverse Reinforcement Learning (IRL) technique to simultaneously build an reward model and a policy model. We show that the proposed algorithms converge to the stationary solutions of the IRL problem. Our results indicate that it is beneficial to leverage reward learning throughout the entire alignment process.
  arXiv  Detail & Related papers  (2024-05-28T07:11:05Z)
• Stochastic Two Points Method for Deep Model Zeroth-order Optimization [32.459322001738144]
  This paper introduces an efficient Two-Point (S2P) approach within the gradient-free regime. We present the theoretical convergence properties of S2P under the general and relaxed smoothness assumptions. We show that VS2P is highly effective in optimizing objectives for deep models.
  arXiv  Detail & Related papers  (2024-02-02T18:39:40Z)
• Towards Constituting Mathematical Structures for Learning to Optimize [101.80359461134087]
  A technique that utilizes machine learning to learn an optimization algorithm automatically from data has gained arising attention in recent years. A generic L2O approach parameterizes the iterative update rule and learns the update direction as a black-box network. While the generic approach is widely applicable, the learned model can overfit and may not generalize well to out-of-distribution test sets. We propose a novel L2O model with a mathematics-inspired structure that is broadly applicable and generalized well to out-of-distribution problems.
  arXiv  Detail & Related papers  (2023-05-29T19:37:28Z)
• Symbolic Learning to Optimize: Towards Interpretability and Scalability [113.23813868412954]
  Recent studies on Learning to Optimize (L2O) suggest a promising path to automating and accelerating the optimization procedure for complicated tasks. Existing L2O models parameterize optimization rules by neural networks, and learn those numerical rules via meta-training. In this paper, we establish a holistic symbolic representation and analysis framework for L2O. We propose a lightweight L2O model that can be meta-trained on large-scale problems and outperformed human-designed and tuneds.
  arXiv  Detail & Related papers  (2022-03-13T06:04:25Z)
• Learning to Optimize: A Primer and A Benchmark [94.29436694770953]
  Learning to optimize (L2O) is an emerging approach that leverages machine learning to develop optimization methods. This article is poised to be the first comprehensive survey and benchmark of L2O for continuous optimization.
  arXiv  Detail & Related papers  (2021-03-23T20:46:20Z)
• Training Stronger Baselines for Learning to Optimize [119.35557905664832]
  We show that even the simplest L2O model could have been trained much better. We leverage off-policy imitation learning to guide the L2O learning, by taking reference to the behavior of analyticals. Our improved training techniques are plugged into a variety of state-of-the-art L2O models, and immediately boost their performance.
  arXiv  Detail & Related papers  (2020-10-18T20:05:48Z)

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.