GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry

• URL: http://arxiv.org/abs/2602.18584v1
• Date: Fri, 20 Feb 2026 19:44:24 GMT
• Title: GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry
• Abstract summary: GIST (Gradient Isometric Subspace Transformation) replaces axis-aligned scaling with robust subspace alignment.<n>We show that GIST matches or outperforms the state-of-the-art baseline with only 0.29% of the storage and 25% of the computational time.
• Score: 4.94446914034065
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Targeted data selection has emerged as a crucial paradigm for efficient instruction tuning, aiming to identify a small yet influential subset of training examples for a specific target task. In practice, influence is often measured through the effect of an example on parameter updates. To make selection scalable, many approaches leverage optimizer statistics (e.g., Adam states) as an axis-aligned surrogate for update geometry (i.e., diagonal precondition), implicitly treating parameters as coordinate-wise independent. We show that this assumption breaks down in parameter-efficient fine-tuning (PEFT) methods such as LoRA. In this setting, the induced optimization geometry exhibits strong cross-parameter coupling with non-trivial off-diagonal interactions, while the task-relevant update directions are confined to a low-dimensional subspace. Motivated by this mismatch, we propose GIST (Gradient Isometric Subspace Transformation), a simple yet principled alternative that replaces axis-aligned scaling with robust subspace alignment. GIST recovers a task-specific subspace from validation gradients via spectral filtering (SVD), projects training gradients into this coupled subspace, and scores examples by their alignment with target directions.Extensive experiments have demonstrated that GIST matches or outperforms the state-of-the-art baseline with only 0.29% of the storage and 25% of the computational time under the same selection budget.

Related papers

• Preference Data Selection for Mitigating the Alignment Tax in Large Language Models [52.18310687523229]
  BALIGN is a balanced data selection strategy that mitigates catastrophic forgetting while optimizing alignment efficacy.<n>By aggregating three key data-centric features into a unified composite risk score, BALIGN systematically filters out high-risk preference samples.<n>Experiments on standard human preference datasets demonstrate that BALIGN strongly preserves foundational capabilities without compromising alignment gains.
  arXiv  Detail & Related papers  (2026-08-25T07:58:42Z)
• A Robust Optimization Approach to Sparse Principal Component Analysis [8.963365635440722]
  We propose Adversarial PCA (AdvPCA), which leverages robust optimization to achieve sparsity.<n>We show that this formulation admits a closed-form reduction, leading to a practical iterative algorithm.<n>By theoretically characterizing the solution, we derive a data-adaptive parameterization that allows the algorithm to perform effectively out of the box.
  arXiv  Detail & Related papers  (2026-06-02T12:14:12Z)
• iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models [14.623213614166259]
  iGSP is a novel framework that achieves efficient adaptation via implicit gradient subspace projection.<n>Experiments on the MTIL benchmark demonstrate that iGSP achieves state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2026-05-19T03:22:14Z)
• DRAFTO: Decoupled Reduced-space and Adaptive Feasibility-repair Trajectory Optimization for Robotic Manipulators [4.0407133618465005]
  This paper introduces a new algorithm for trajectory optimization, Decoupled Reduced-space and Adaptive Feasibility-repair Trajectory Optimization (DRAFTO)<n>To reduce the number of repeated constrained optimizations while handling joint-limit feasibility, the optimization is decoupled into a reduced-space Gauss-Newton (GN) descent.<n>The results of our benchmark tests against optimization-based planners, such as CHOMP, TrajOpt, GPMP2, and FACTO, validate the high efficiency and reliability across diverse scenarios and tasks.
  arXiv  Detail & Related papers  (2026-03-10T20:24:42Z)
• Two-Stage Optimizer-Aware Online Data Selection for Large Language Models [49.576993784867035]
  We propose a principled-aware framework for gradient-based online data selection and reweighting in large language model fine-tuning.<n>Our key idea is to view online selection not as static sample ranking, but as shaping the next target-oriented update under the state.<n> Experiments show that our method consistently improves convergence and downstream performance over existing online data selection baselines under the same data budget.
  arXiv  Detail & Related papers  (2026-03-08T21:46:16Z)
• FACTO: Function-space Adaptive Constrained Trajectory Optimization for Robotic Manipulators [4.0407133618465005]
  This paper introduces Function-space Adaptive Constrained Trajectory Optimization (FACTO) for single- and multi-arm manipulators.<n>To address nonlinearity, FACTO uses a Gauss-Newton approximation with exponential moving averaging, yielding a smoothed quadratic subproblem.<n>The experimental evaluation of FACTO on Franka robots verifies the feasibility of deployment.
  arXiv  Detail & Related papers  (2026-02-23T16:38:13Z)
• Tangent Space Fine-Tuning for Directional Preference Alignment in Large Language Models [0.2538209532048867]
  Our goal is to enable large language models to balance human preference dimensions through principled and controllable alignment.<n>We propose Tangent-Space Direct Preference Optimization (TS-DPO), which performs DPO within a locally linear regime to learn per-objective update directions.
  arXiv  Detail & Related papers  (2026-02-01T09:56:28Z)
• Latent Geometry of Taste: Scalable Low-Rank Matrix Factorization for Recommender Systems [0.0]
  This work investigates the latent geometry of user preferences using the MovieLens 32M dataset.<n>We demonstrate that constrained low-rank models significantly outperform higher dimensional counterparts in terms of ranking precision.<n>We validate the system's practical utility in a cold-start scenario, introducing a tunable scoring parameter to manage the trade-off between popularity bias and personalized affinity effectively.
  arXiv  Detail & Related papers  (2026-01-06T23:42:40Z)
• Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios [54.58186816693791]
  environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption.<n>We propose a new mechanism, converting the fine-tuning process to a specific- parameter generation.<n>In particular, we first design a dual-path LoRA-based domain-aware adapter that disentangles features into domain-invariant and domain-specific components.
  arXiv  Detail & Related papers  (2025-06-30T17:14:12Z)
• Leveraging Axis-Aligned Subspaces for High-Dimensional Bayesian Optimization with Group Testing [6.5202942559480075]
  We propose a group testing ( GT) approach to identify active variables to facilitate efficient optimization in high-dimensional domains.<n>We extend the well-established GT theory to functions over continuous domains.<n>In the second phase, GTBO guides optimization by placing more importance on the active dimensions.
  arXiv  Detail & Related papers  (2025-04-08T15:00:15Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• TAROT: Targeted Data Selection via Optimal Transport [64.56083922130269]
  TAROT is a targeted data selection framework grounded in optimal transport theory.<n>Previous targeted data selection methods rely on influence-based greedys to enhance domain-specific performance.<n>We evaluate TAROT across multiple tasks, including semantic segmentation, motion prediction, and instruction tuning.
  arXiv  Detail & Related papers  (2024-11-30T10:19:51Z)
• Adaptive Preference Scaling for Reinforcement Learning with Human Feedback [103.36048042664768]
  Reinforcement learning from human feedback (RLHF) is a prevalent approach to align AI systems with human values. We propose a novel adaptive preference loss, underpinned by distributionally robust optimization (DRO) Our method is versatile and can be readily adapted to various preference optimization frameworks.
  arXiv  Detail & Related papers  (2024-06-04T20:33:22Z)
• SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration [77.13381026159111]
  We propose SPARE, a novel formulation that utilizes a symmetrized point-to-plane distance for robust non-rigid registration.<n>The proposed method greatly improves the accuracy of non-rigid registration problems and maintains relatively high solution efficiency.
  arXiv  Detail & Related papers  (2024-05-30T15:55:04Z)
• Uncertainty-Guided Alignment for Unsupervised Domain Adaptation in Regression [5.437298646956505]
  Unsupervised Domain Adaptation for Regression (UDAR) aims to adapt models from a labeled source domain to an unlabeled target domain for regression tasks. Traditional feature alignment methods, successful in classification, often prove ineffective for regression due to the correlated nature of regression features. We propose Uncertainty-Guided Alignment (UGA), a novel method that integrates predictive uncertainty into the feature alignment process.
  arXiv  Detail & Related papers  (2024-01-24T14:55:02Z)
• Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm [132.9949120482274]
  This paper focuses on the selection of samples for annotation in the pretraining-finetuning paradigm. We propose a novel method called ActiveFT for active finetuning task to select a subset of data distributing similarly with the entire unlabeled pool. Extensive experiments show the leading performance and high efficiency of ActiveFT superior to baselines on both image classification and semantic segmentation.
  arXiv  Detail & Related papers  (2023-03-25T07:17:03Z)
• Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation [14.050836886292869]
  We introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation. We verify the effectiveness of such methods in the autonomous driving setting.
  arXiv  Detail & Related papers  (2021-04-06T16:07:22Z)
• Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic [5.395127324484869]
  SplitSGD is a new dynamic learning schedule for optimization. The method decreases the learning rate for better adaptation to the local geometry of the objective function. It essentially does not incur additional computational cost than standard SGD.
  arXiv  Detail & Related papers  (2019-10-18T19:38:53Z)

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.