A Hessian-informed hyperparameter optimization for differential learning rate
- URL: http://arxiv.org/abs/2501.06954v1
- Date: Sun, 12 Jan 2025 22:21:06 GMT
- Title: A Hessian-informed hyperparameter optimization for differential learning rate
- Authors: Shiyun Xu, Zhiqi Bu, Yiliang Zhang, Ian Barnett,
- Abstract summary: Hessian-informed differential learning rate (Hi-DLR) is a technique that applies different learning rates to different model parameters.
Hi-DLR can improve the convergence by dynamically determining the learning rates during the training.
It also exhibits comparable performance on various full model training tasks.
- Score: 10.43211367988483
- License:
- Abstract: Differential learning rate (DLR), a technique that applies different learning rates to different model parameters, has been widely used in deep learning and achieved empirical success via its various forms. For example, parameter-efficient fine-tuning (PEFT) applies zero learning rates to most parameters so as to significantly save the computational cost. At the core, DLR leverages the observation that different parameters can have different loss curvature, which is hard to characterize in general. We propose the Hessian-informed differential learning rate (Hi-DLR), an efficient approach that solves the hyperparameter optimization (HPO) of learning rates and captures the loss curvature for any model and optimizer adaptively. Given a proper grouping of parameters, we empirically demonstrate that Hi-DLR can improve the convergence by dynamically determining the learning rates during the training. Furthermore, we can quantify the influence of different parameters and freeze the less-contributing parameters, which leads to a new PEFT that automatically adapts to various tasks and models. Additionally, Hi-DLR also exhibits comparable performance on various full model training tasks.
Related papers
- 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.
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) - A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning [11.929813643723413]
This work proposes a new empirical methodology for studying, comparing, and quantifying the sensitivity of an algorithm's performance to hyperparameter tuning.
The results suggest that several algorithmic performance improvements may, in fact, be a result of an increased reliance on hyperparameter tuning.
arXiv Detail & Related papers (2024-12-10T03:55:18Z) - Scaling Exponents Across Parameterizations and Optimizers [94.54718325264218]
We propose a new perspective on parameterization by investigating a key assumption in prior work.
Our empirical investigation includes tens of thousands of models trained with all combinations of threes.
We find that the best learning rate scaling prescription would often have been excluded by the assumptions in prior work.
arXiv Detail & Related papers (2024-07-08T12:32:51Z) - ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections [59.839926875976225]
We propose the ETHER transformation family, which performs Efficient fineTuning via HypErplane Reflections.
In particular, we introduce ETHER and its relaxation ETHER+, which match or outperform existing PEFT methods with significantly fewer parameters.
arXiv Detail & Related papers (2024-05-30T17:26:02Z) - Hyperparameter Tuning for Causal Inference with Double Machine Learning:
A Simulation Study [4.526082390949313]
We empirically assess the relationship between the predictive performance of machine learning methods and the resulting causal estimation.
We conduct an extensive simulation study using data from the 2019 Atlantic Causal Inference Conference Data Challenge.
arXiv Detail & Related papers (2024-02-07T09:01:51Z) - Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared
Pre-trained Language Models [109.06052781040916]
We introduce a technique to enhance the inference efficiency of parameter-shared language models.
We also propose a simple pre-training technique that leads to fully or partially shared models.
Results demonstrate the effectiveness of our methods on both autoregressive and autoencoding PLMs.
arXiv Detail & Related papers (2023-10-19T15:13:58Z) - No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for
Training Large Transformer Models [132.90062129639705]
We propose a novel training strategy that encourages all parameters to be trained sufficiently.
A parameter with low sensitivity is redundant, and we improve its fitting by increasing its learning rate.
In contrast, a parameter with high sensitivity is well-trained and we regularize it by decreasing its learning rate to prevent further overfitting.
arXiv Detail & Related papers (2022-02-06T00:22:28Z) - Adaptive Gradient Method with Resilience and Momentum [120.83046824742455]
We propose an Adaptive Gradient Method with Resilience and Momentum (AdaRem)
AdaRem adjusts the parameter-wise learning rate according to whether the direction of one parameter changes in the past is aligned with the direction of the current gradient.
Our method outperforms previous adaptive learning rate-based algorithms in terms of the training speed and the test error.
arXiv Detail & Related papers (2020-10-21T14:49:00Z)
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.