Learning to Fine-tune Foundation Models under Resource Limitations

• URL: http://arxiv.org/abs/2607.10694v1
• Date: Sun, 12 Jul 2026 10:32:32 GMT
• Title: Learning to Fine-tune Foundation Models under Resource Limitations
• Abstract summary: We study the problem of optimal continual fine-tuning for a pre-trained Foundation Model deployed at a resource-limited device.<n>Our objective is to learn an optimal policy that determines emphwhen to fine-tune the model under a finite compute budget.<n> Experiments with a large pre-trained model on a widely-used text classification dataset demonstrate that our method consistently outperforms fine-tuning approaches with the same compute budget.
• Score: 2.7071541526963805
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We study the problem of optimal continual fine-tuning for a pre-trained Foundation Model deployed at a resource-limited device. At each time slot, a new batch of training data arrives, and the controller is faced with two options: either use the data to fine-tune the model and incur a compute cost, or do not fine-tune the model and discard the data. After the decision, the performance of the current model is measured in terms of an application-specific performance metric such as classification accuracy. Our objective is to learn an optimal policy that determines \emph{when to fine-tune the model} on a single task (e.g., sentiment analysis), under a finite compute budget. We formulate this online decision-making problem as a constrained Markov Decision Process, where the system state captures three essential aspects: (\textit{i}) model's performance, (\textit{ii}) computational budget, and (\textit{iii}) data distribution relevance to historic data encountered up to that point. The transition to the next state is stochastic and therefore, we propose a reinforcement learning-based method to solve this problem, namely the \emph{actor-critic} algorithm. We also consider the special case where the performance of fine-tuning for a given model can be predicted or estimated prior to decision; in this case the problem becomes a Dynamic Programming one. Experiments with a large pre-trained model on a widely-used text classification dataset demonstrate that our method consistently outperforms fine-tuning approaches with the same compute budget by more than $4\%$ in terms of accuracy and achieves $97\%$ of full-parameter fine-tuning accuracy while requiring only $25\%$ of the fine-tuning steps.

Related papers

• The Challenger: When Do New Data Sources Justify Switching Machine Learning Models? [2.7998963147546143]
  We study the problem of deciding whether an organization should replace a trained incumbent model with a challenger relying on newly available features.<n>We develop a unified economic and statistical framework that links learning-curve dynamics, data-acquisition and retraining costs, and discounting of future gains.
  arXiv  Detail & Related papers  (2025-12-20T15:03:40Z)
• e1: Learning Adaptive Control of Reasoning Effort [88.51897900019485]
  Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning.<n>Users may prefer to allocate different amounts of reasoning effort depending on how they value output quality versus latency and cost.<n>We propose Adaptive Effort Control, a self-adaptive reinforcement learning method that trains models to use a user-specified fraction of tokens.
  arXiv  Detail & Related papers  (2025-10-30T23:12:21Z)
• Intention-Conditioned Flow Occupancy Models [80.42634994902858]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• Entropy-Based Adaptive Weighting for Self-Training [15.089334734753677]
  We propose Entropy-Based Adaptive Weighting for Self-Training (EAST)<n>EAST is an adaptive weighting strategy designed to prioritize uncertain data during self-training.<n>We evaluate our approach on GSM8K and MATH benchmarks.
  arXiv  Detail & Related papers  (2025-03-31T10:04:35Z)
• Value-Based Deep RL Scales Predictably [100.21834069400023]
  We show that value-based off-policy RL methods are predictable despite community lore regarding their pathological behavior.<n>We validate our approach using three algorithms: SAC, BRO, and PQL on DeepMind Control, OpenAI gym, and IsaacGym.
  arXiv  Detail & Related papers  (2025-02-06T18:59:47Z)
• Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference [55.150117654242706]
  We show that model selection for computation-aware GPs trained on 1.8 million data points can be done within a few hours on a single GPU.<n>As a result of this work, Gaussian processes can be trained on large-scale datasets without significantly compromising their ability to quantify uncertainty.
  arXiv  Detail & Related papers  (2024-11-01T21:11:48Z)
• Compute-Constrained Data Selection [77.06528009072967]
  We find that many powerful data selection methods are almost never compute-optimal.<n>For compute-optimal training, we find that perplexity and gradient data selection require training-to-selection model size ratios of 5x and 10x, respectively.
  arXiv  Detail & Related papers  (2024-10-21T17:11:21Z)
• Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing [20.445496441396028]
  We introduce a novel framework combining model cascading and inference-time self-testing algorithms to find multiple near-optimal self-testing options on the cost-accuracy tradeoff.<n>Our approach leverages self-generated tests to both enhance accuracy and evaluate model cascading decisions.<n> Experimental results show that our cascading approach reduces costs by an average of 26%, and up to 70% in the best case.
  arXiv  Detail & Related papers  (2024-05-24T16:20:04Z)
• LAVA: Data Valuation without Pre-Specified Learning Algorithms [20.578106028270607]
  We introduce a new framework that can value training data in a way that is oblivious to the downstream learning algorithm. We develop a proxy for the validation performance associated with a training set based on a non-conventional class-wise Wasserstein distance between training and validation sets. We show that the distance characterizes the upper bound of the validation performance for any given model under certain Lipschitz conditions.
  arXiv  Detail & Related papers  (2023-04-28T19:05:16Z)
• Sufficiently Accurate Model Learning for Planning [119.80502738709937]
  This paper introduces the constrained Sufficiently Accurate model learning approach. It provides examples of such problems, and presents a theorem on how close some approximate solutions can be. The approximate solution quality will depend on the function parameterization, loss and constraint function smoothness, and the number of samples in model learning.
  arXiv  Detail & Related papers  (2021-02-11T16:27:31Z)
• On Statistical Efficiency in Learning [37.08000833961712]
  We address the challenge of model selection to strike a balance between model fitting and model complexity. We propose an online algorithm that sequentially expands the model complexity to enhance selection stability and reduce cost. Experimental studies show that the proposed method has desirable predictive power and significantly less computational cost than some popular methods.
  arXiv  Detail & Related papers  (2020-12-24T16:08:29Z)
• The Right Tool for the Job: Matching Model and Instance Complexities [62.95183777679024]
  As NLP models become larger, executing a trained model requires significant computational resources incurring monetary and environmental costs. We propose a modification to contextual representation fine-tuning which, during inference, allows for an early (and fast) "exit" We test our proposed modification on five different datasets in two tasks: three text classification datasets and two natural language inference benchmarks.
  arXiv  Detail & Related papers  (2020-04-16T04:28:08Z)

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.