Cheap Thrills: Effective Amortized Optimization Using Inexpensive Labels

• URL: http://arxiv.org/abs/2603.05495v1
• Date: Thu, 05 Mar 2026 18:58:39 GMT
• Title: Cheap Thrills: Effective Amortized Optimization Using Inexpensive Labels
• Authors: Khai Nguyen, Petros Ellinas, Anvita Bhagavathula, Priya Donti,
• Abstract summary: We propose "cheap imperfect labels," then perform pretraining, and refine the model through self-supervised learning to improve overall performance.<n>Our theoretical analysis and empirically-based criterion show that labeled data only need place the model within a basin of attraction.<n>We show it yields faster convergence; improved accuracy; high-quality optimality; and up to 59x reductions in total offline cost.
• Score: 20.00525916892172
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: To scale the solution of optimization and simulation problems, prior work has explored machine-learning surrogates that inexpensively map problem parameters to corresponding solutions. Commonly used approaches, including supervised and self-supervised learning with either soft or hard feasibility enforcement, face inherent challenges such as reliance on expensive, high-quality labels or difficult optimization landscapes. To address their trade-offs, we propose a novel framework that first collects "cheap" imperfect labels, then performs supervised pretraining, and finally refines the model through self-supervised learning to improve overall performance. Our theoretical analysis and merit-based criterion show that labeled data need only place the model within a basin of attraction, confirming that only modest numbers of inexact labels and training epochs are required. We empirically validate our simple three-stage strategy across challenging domains, including nonconvex constrained optimization, power-grid operation, and stiff dynamical systems, and show that it yields faster convergence; improved accuracy, feasibility, and optimality; and up to 59x reductions in total offline cost.

Related papers

• Labels or Preferences? Budget-Constrained Learning with Human Judgments over AI-Generated Outputs [17.028710603629026]
  We show how to optimally allocate a fixed annotation budget between ground-truth labels and pairwise preferences in AI.<n>We introduce Preference-Calibrated Active Learning (PCAL), a novel robustness method that learns optimal data acquisition strategy.<n>This work provides a principled and statistically efficient approach for budget-constrained learning in modern AI.
  arXiv  Detail & Related papers  (2026-01-19T23:23:29Z)
• Online Inference of Constrained Optimization: Primal-Dual Optimality and Sequential Quadratic Programming [55.848340925419286]
  We study online statistical inference for the solutions of quadratic optimization problems with equality and inequality constraints.<n>We develop a sequential programming (SSQP) method to solve these problems, where the step direction is computed by sequentially performing an approximation of the objective and a linear approximation of the constraints.<n>We show that our method global almost moving-average convergence and exhibits local normality with an optimal primal-dual limiting matrix in the sense of Hjek and Le Cam.
  arXiv  Detail & Related papers  (2025-11-27T06:16:17Z)
• HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization [4.249024052507976]
  We introduce a novel framework that reformulates hard-constrained sampling as a trajectory optimization problem.<n>Our key insight is to leverage numerical optimal control to steer the sampling trajectory so that constraints are satisfied precisely at the terminal time.<n>Our algorithm, which we name $textitHardFlow$, substantially outperforms existing methods in both constraint satisfaction and sample quality.
  arXiv  Detail & Related papers  (2025-11-11T16:33:57Z)
• AdaptiveLLM: A Framework for Selecting Optimal Cost-Efficient LLM for Code-Generation Based on CoT Length [5.856039862078523]
  We introduce AdaptiveLLM, a framework that dynamically selects optimal Large Language Models (LLMs) for a given coding task by automatically assessing task difficulty.<n>Our framework first estimates task difficulty using Chain-of-Thought lengths generated by reasoning model, clusters these into three difficulty levels via k-means, and fine-tunes CodeBERT to embed difficulty-aware features.<n>Our framework achieves a 7.86% improvement in pass@1 score while reducing resource consumption by 88.9% compared to baseline method ComplexityNet.
  arXiv  Detail & Related papers  (2025-06-12T09:43:48Z)
• Scalable Chain of Thoughts via Elastic Reasoning [61.75753924952059]
  Elastic Reasoning is a novel framework for scalable chain of thoughts.<n>It separates reasoning into two phases--thinking and solution--with independently allocated budgets.<n>Our approach produces more concise and efficient reasoning even in unconstrained settings.
  arXiv  Detail & Related papers  (2025-05-08T15:01:06Z)
• Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models [79.84205827056907]
  We present Self-Steering Optimization ($SSO$), an algorithm that autonomously generates high-quality preference data.<n>$SSO$ employs a specialized optimization objective to build a data generator from the policy model itself, which is used to produce accurate and on-policy data.<n>Our evaluation shows that $SSO$ consistently outperforms baselines in human preference alignment and reward optimization.
  arXiv  Detail & Related papers  (2024-10-22T16:04:03Z)
• Jump Diffusion-Informed Neural Networks with Transfer Learning for Accurate American Option Pricing under Data Scarcity [1.998862666797032]
  This study presents a comprehensive framework for American option pricing consisting of six interrelated modules. The framework combines nonlinear optimization algorithms, analytical and numerical models, and neural networks to improve pricing performance. The proposed model shows superior performance in pricing deep out-of-the-money options.
  arXiv  Detail & Related papers  (2024-09-26T17:50:12Z)
• Memory-Enhanced Neural Solvers for Routing Problems [8.255381359612885]
  We present MEMENTO, an approach that leverages memory to improve the search of neural solvers at inference.<n>We validate its effectiveness on the Traveling Salesman and Capacitated Vehicle Routing problems, demonstrating its superiority over tree-search and policy-gradient fine-tuning.<n>We successfully train all RL auto-regressive solvers on large instances, and verify MEMENTO's scalability and data-efficiency.
  arXiv  Detail & Related papers  (2024-06-24T08:18:19Z)
• OTClean: Data Cleaning for Conditional Independence Violations using Optimal Transport [51.6416022358349]
  sys is a framework that harnesses optimal transport theory for data repair under Conditional Independence (CI) constraints. We develop an iterative algorithm inspired by Sinkhorn's matrix scaling algorithm, which efficiently addresses high-dimensional and large-scale data.
  arXiv  Detail & Related papers  (2024-03-04T18:23:55Z)
• Training Over-parameterized Models with Non-decomposable Objectives [46.62273918807789]
  We propose new cost-sensitive losses that extend the classical idea of logit adjustment to handle more general cost matrices. Our losses are calibrated, and can be further improved with distilled labels from a teacher model.
  arXiv  Detail & Related papers  (2021-07-09T19:29:33Z)
• Semi-Supervised Learning with Meta-Gradient [123.26748223837802]
  We propose a simple yet effective meta-learning algorithm in semi-supervised learning. We find that the proposed algorithm performs favorably against state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-08T08:48:56Z)

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.