Efficient Hyperparameter Tuning via Trajectory Invariance Principle

• URL: http://arxiv.org/abs/2509.25049v1
• Date: Mon, 29 Sep 2025 17:01:19 GMT
• Title: Efficient Hyperparameter Tuning via Trajectory Invariance Principle
• Authors: Bingrui Li, Jiaxin Wen, Zhanpeng Zhou, Jun Zhu, Jianfei Chen,
• Abstract summary: We identify a phenomenon we call trajectory invariance, where pre-training loss curves, gradient noise, and gradient norm exhibit invariance--closely overlapping--with respect to a quantity that combines learning rate and weight decay.<n>This phenomenon effectively reduces the original two-dimensional hyper parameter space to one dimension, yielding an efficient tuning rule.<n>Overall, our work proposes new principles for efficient tuning and inspires future research on scaling laws.
• Score: 35.90572735438328
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As hyperparameter tuning becomes increasingly costly at scale, efficient tuning methods are essential. Yet principles for guiding hyperparameter tuning remain limited. In this work, we seek to establish such principles by considering a broad range of hyperparameters, including batch size, learning rate, and weight decay. We identify a phenomenon we call trajectory invariance, where pre-training loss curves, gradient noise, and gradient norm exhibit invariance--closely overlapping--with respect to a quantity that combines learning rate and weight decay. This phenomenon effectively reduces the original two-dimensional hyperparameter space to one dimension, yielding an efficient tuning rule: follow the salient direction revealed by trajectory invariance. Furthermore, we refine previous scaling laws and challenge several existing viewpoints. Overall, our work proposes new principles for efficient tuning and inspires future research on scaling laws.

Related papers

• Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport [51.56484100374058]
  Post-deployment, user preferences can evolve, making initial settings undesirable.<n>We learn, from observed data, how a NN's conditional output distribution changes with its hyper parameters.<n>We construct a surrogate model that approximates the NN at unobserved hyper parameters.
  arXiv  Detail & Related papers  (2026-03-02T11:55:02Z)
• Weight Updates as Activation Shifts: A Principled Framework for Steering [54.70188910511715]
  Activation steering promises to be an extremely parameter-efficient form of adaptation, but its effectiveness depends on critical design choices.<n>We establish a first-order equivalence between activation-space interventions and weight-space updates, deriving the conditions under which activation steering can replicate fine-tuning behavior.<n>This equivalence yields a principled framework for steering design and identifies the post-block output as a theoretically-backed and highly expressive intervention site.
  arXiv  Detail & Related papers  (2026-02-28T02:50:04Z)
• High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning [57.85676271833619]
  Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning.<n>We present textbfSMoA, a high-rank textbfStructured textbfMOdulation textbfAdapter that uses fewer trainable parameters while maintaining a higher rank.
  arXiv  Detail & Related papers  (2026-01-12T13:06:17Z)
• Allocation of Parameters in Transformers [31.7433692306049]
  We investigate how the model parameters -- mainly attention heads and head dimensions -- should be allocated across layers to balance expressivity and efficiency.<n>We prove the emphsaturation behavior of softmax activations, supported by both theory and experiments.<n>We propose principled strategies for allocating attention heads and dimensions across Transformers' layers.
  arXiv  Detail & Related papers  (2025-10-04T11:22:16Z)
• Weight Spectra Induced Efficient Model Adaptation [54.8615621415845]
  Fine-tuning large-scale foundation models incurs prohibitive computational costs.<n>We show that fine-tuning predominantly amplifies the top singular values while leaving the remainder largely intact.<n>We propose a novel method that leverages learnable rescaling of top singular directions.
  arXiv  Detail & Related papers  (2025-05-29T05:03:29Z)
• PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization [35.922096876707975]
  PACE is a generalization of PArameter-efficient fine-tuning with Consistency rEgularization.<n>It implicitly regularizes gradients for enhanced generalization, but also implicitly aligns the fine-tuned and pre-trained models to retain knowledge.<n>It also improves LoRA in text classification (GLUE) and mathematical reasoning.
  arXiv  Detail & Related papers  (2024-09-25T17:56:00Z)
• Propulsion: Steering LLM with Tiny Fine-Tuning [0.0]
  We propose Propulsion, a novel parameter efficient fine-tuning (PEFT) method to optimize task-specific performance.<n>Inspired by the concept of controlled adjustments in physical motion, Propulsion selectively re-scales specific dimensions of a pre-trained model.<n>Our theoretical analysis, supported by Neural Tangent Kernel (NTK) theory, shows that Propulsion approximates the performance of full fine-tuning with far fewer trainable parameters.
  arXiv  Detail & Related papers  (2024-09-17T06:51:59Z)
• Sparse is Enough in Fine-tuning Pre-trained Large Language Models [98.46493578509039]
  We propose a gradient-based sparse fine-tuning algorithm, named Sparse Increment Fine-Tuning (SIFT) We validate its effectiveness on a range of tasks including the GLUE Benchmark and Instruction-tuning.
  arXiv  Detail & Related papers  (2023-12-19T06:06:30Z)
• Improve Noise Tolerance of Robust Loss via Noise-Awareness [60.34670515595074]
  We propose a meta-learning method which is capable of adaptively learning a hyper parameter prediction function, called Noise-Aware-Robust-Loss-Adjuster (NARL-Adjuster for brevity) Four SOTA robust loss functions are attempted to be integrated with our algorithm, and comprehensive experiments substantiate the general availability and effectiveness of the proposed method in both its noise tolerance and performance.
  arXiv  Detail & Related papers  (2023-01-18T04:54:58Z)
• META-STORM: Generalized Fully-Adaptive Variance Reduced SGD for Unbounded Functions [23.746620619512573]
  Recent work overcomes the effect of having to compute gradients of "megabatches" Work is widely used after update with competitive deep learning tasks.
  arXiv  Detail & Related papers  (2022-09-29T15:12:54Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.