CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models

• URL: http://arxiv.org/abs/2510.15962v1
• Date: Sat, 11 Oct 2025 20:05:56 GMT
• Title: CTR-LoRA: Curvature-Aware and Trust-Region Guided Low-Rank Adaptation for Large Language Models
• Abstract summary: CTR-LoRA integrates rank scheduling with stability-aware optimization.<n>Experiments on multiple open-source backbones (7B-13B) show consistent improvements over strong PEFT baselines.
• Score: 23.34193229321038
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Parameter-efficient fine-tuning (PEFT) has become the standard approach for adapting large language models under limited compute and memory budgets. Although previous methods improve efficiency through low-rank updates, quantization, or heuristic budget reallocation, they often decouple the allocation of capacity from the way updates evolve during training. In this work, we introduce CTR-LoRA, a framework guided by curvature trust region that integrates rank scheduling with stability-aware optimization. CTR-LoRA allocates parameters based on marginal utility derived from lightweight second-order proxies and constrains updates using a Fisher/Hessian-metric trust region. Experiments on multiple open-source backbones (7B-13B), evaluated on both in-distribution and out-of-distribution benchmarks, show consistent improvements over strong PEFT baselines. In addition to increased accuracy, CTR-LoRA enhances training stability, reduces memory requirements, and achieves higher throughput, positioning it on the Pareto frontier of performance and efficiency. These results highlight a principled path toward more robust and deployable PEFT.

Related papers

• Rethinking the Divergence Regularization in LLM RL [56.952725733148746]
  Reinforcement learning (RL) has become a key component of post-training large language models (LLMs)<n>We propose Divergence Regularized Policy Optimization (DRPO), which replaces the hard mask with a smooth advantage-weighted quadratic regularizer on policy shift.<n>DRPO preserves the same trust-region geometry as DPPO while inducing bounded, continuous gradient weights.
  arXiv  Detail & Related papers  (2026-06-08T17:58:23Z)
• Explicit Critic Guidance for Aligning Diffusion Models [27.6704888666835]
  We propose a state-aligned latent actor-critic framework for diffusion post-training.<n>Our method consistently outperforms prior group-relative RL and actor-critic baselines on single-reward and multi-reward benchmarks.
  arXiv  Detail & Related papers  (2026-05-26T22:20:51Z)
• Curvature-Guided LoRA: Steering in the pretrained NTK subspace [60.35296431630704]
  We introduce the prediction alignment problem, aiming to match the predictor obtained via PEFT to that of full fine-tuning at the level of outputs.<n>We show that this objective naturally leads to a curvature-aware, second-order formulation, where optimal low-rank updates correspond to a Newton-like, curvature-whitened gradient.<n>Based on this insight, we propose Curvature-Guided LoRA (CG-LoRA), which selects and scales adaptation directions using local curvature information.
  arXiv  Detail & Related papers  (2026-03-31T14:46:39Z)
• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• GRIT -- Geometry-Aware PEFT with K-FACPreconditioning, Fisher-Guided Reprojection, andDynamic Rank Adaptation [4.748720471060117]
  GRIT is a curvature-aware LoRA procedure that preserves the LoRA parameterization.<n>It matches or surpasses LoRA and QLoRA while reducing trainable parameters by 46% on average.<n>GRIT yields lower drift and a better updates-vs-retention frontier than strong PEFT-optimizer baselines.
  arXiv  Detail & Related papers  (2026-01-01T06:31:54Z)
• Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT [19.773848189002965]
  DoRA method enhances performance by decomposing weight updates into magnitude and direction.<n>In this work, we identify that DoRA's success stems from its capacity to increase the singular value entropy of the weight update matrix.<n>We reformulate DoRA into a mathematically equivalent and more efficient matrix form, revealing it as a learnable weight conditioning method.
  arXiv  Detail & Related papers  (2025-10-28T12:52:54Z)
• DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks [47.58150560549918]
  Weight-Decomposed Low-Rank Adaptation (DoRA) has been shown to improve both the learning capacity and training stability of the vanilla Low-Rank Adaptation (LoRA) method.<n>We propose DoRAN, a new variant of DoRA designed to further stabilize training and boost the sample efficiency of DoRA.
  arXiv  Detail & Related papers  (2025-10-05T19:27:48Z)
• TROLL: Trust Regions improve Reinforcement Learning for Large Language Models [25.03342193102256]
  On-policy Reinforcement Learning (RL) with PPO-like clip objectives has become the standard choice for fine-tuning of large language models (LLMs)<n>We replace the clip objective with a novel discrete differentiable trust region projection, which provides principled token-level KL constraints.<n>Our approach, Trust Region Optimization for Large Language Models (TROLL), serves as a direct replacement for PPO-like clipping during training and does not alter the model's inference behavior.
  arXiv  Detail & Related papers  (2025-10-04T14:14:20Z)
• Don't Forget the Nonlinearity: Unlocking Activation Functions in Efficient Fine-Tuning [82.16625951603315]
  NoRA replaces fixed activations with learnable rational functions and applies structured low-rank updates to numerator and denominator coefficients.<n>On vision transformers trained on CIFAR-10 and CIFAR-100, NoRA matches or exceeds full fine-tuning while updating only 0.4% of parameters.<n>NoRA constrains adaptation to a low-dimensional functional subspace, implicitly regularizing update magnitude and direction.
  arXiv  Detail & Related papers  (2025-09-16T16:47:03Z)
• From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices [3.4233698915405544]
  This paper benchmarks and analyzes popular PEFT methods on convolutional architectures typically deployed in resource-constrained edge environments.<n>We find that the evaluated PEFT methods are only half as memory-efficient when applied to depthwise-separable convolution architectures.
  arXiv  Detail & Related papers  (2025-07-31T13:23:21Z)
• Robust Federated Finetuning of Foundation Models via Alternating Minimization of LoRA [14.789886179102425]
  RoLoRA is a robust federated fine-tuning framework that utilizes an alternating approach for LoRA. Our results indicate that RoLoRA not only presents the communication benefits but also substantially enhances the robustness and effectiveness in multiple federated fine-tuning scenarios.
  arXiv  Detail & Related papers  (2024-09-04T00:20:55Z)
• Sparse Low-rank Adaptation of Pre-trained Language Models [79.74094517030035]
  We introduce sparse low-rank adaptation (SoRA) that enables dynamic adjustments to the intrinsic rank during the adaptation process. Our approach strengthens the representation power of LoRA by initializing it with a higher rank, while efficiently taming a temporarily increased number of parameters. Our experimental results demonstrate that SoRA can outperform other baselines even with 70% retained parameters and 70% training time.
  arXiv  Detail & Related papers  (2023-11-20T11:56:25Z)
• AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning [143.23123791557245]
  Fine-tuning large pre-trained language models on downstream tasks has become an important paradigm in NLP. We propose AdaLoRA, which adaptively allocates the parameter budget among weight matrices according to their importance score. We conduct extensive experiments with several pre-trained models on natural language processing, question answering, and natural language generation to validate the effectiveness of AdaLoRA.
  arXiv  Detail & Related papers  (2023-03-18T22:36:25Z)
• DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models [152.29364079385635]
  As pre-trained models grow bigger, the fine-tuning process can be time-consuming and computationally expensive. We propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning and (ii) resource-efficient inference.
  arXiv  Detail & Related papers  (2021-10-30T03:29:47Z)

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.