AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient
Hyper-parameter Tuning
- URL: http://arxiv.org/abs/2203.08212v1
- Date: Tue, 15 Mar 2022 19:25:01 GMT
- Title: AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient
Hyper-parameter Tuning
- Authors: Krishnateja Killamsetty, Guttu Sai Abhishek, Aakriti, Alexandre V.
Evfimievski, Lucian Popa, Ganesh Ramakrishnan, Rishabh Iyer
- Abstract summary: We propose a gradient-based subset selection framework for hyper- parameter tuning.
We show that using gradient-based data subsets for hyper- parameter tuning achieves significantly faster turnaround times and speedups of 3$times$-30$times$.
- Score: 72.54359545547904
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Deep neural networks have seen great success in recent years; however,
training a deep model is often challenging as its performance heavily depends
on the hyper-parameters used. In addition, finding the optimal hyper-parameter
configuration, even with state-of-the-art (SOTA) hyper-parameter optimization
(HPO) algorithms, can be time-consuming, requiring multiple training runs over
the entire dataset for different possible sets of hyper-parameters. Our central
insight is that using an informative subset of the dataset for model training
runs involved in hyper-parameter optimization, allows us to find the optimal
hyper-parameter configuration significantly faster. In this work, we propose
AUTOMATA, a gradient-based subset selection framework for hyper-parameter
tuning. We empirically evaluate the effectiveness of AUTOMATA in
hyper-parameter tuning through several experiments on real-world datasets in
the text, vision, and tabular domains. Our experiments show that using
gradient-based data subsets for hyper-parameter tuning achieves significantly
faster turnaround times and speedups of 3$\times$-30$\times$ while achieving
comparable performance to the hyper-parameters found using the entire dataset.
Related papers
- 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) - Hyper-Parameter Auto-Tuning for Sparse Bayesian Learning [72.83293818245978]
We design and learn a neural network (NN)-based auto-tuner for hyper- parameter tuning in sparse Bayesian learning.
We show that considerable improvement in convergence rate and recovery performance can be achieved.
arXiv Detail & Related papers (2022-11-09T12:34:59Z) - Towards Robust and Automatic Hyper-Parameter Tunning [39.04604349338802]
We introduce a new class of HPO method and explore how the low-rank factorization of intermediate layers of a convolutional network can be used to define an analytical response surface.
We quantify how this surface behaves as a surrogate to model performance and can be solved using a trust-region search algorithm, which we call autoHyper.
arXiv Detail & Related papers (2021-11-28T05:27:34Z) - Automatic prior selection for meta Bayesian optimization with a case
study on tuning deep neural network optimizers [47.013395100497775]
We propose a principled approach to solve such expensive hyperparameter tuning problems efficiently.
Key to the performance of BO is specifying and refining a distribution over functions, which is used to reason about the optima of the underlying function being optimized.
We verify our approach in realistic model training setups by training tens of thousands of configurations of near-state-of-the-art models on popular image and text datasets.
arXiv Detail & Related papers (2021-09-16T20:46:26Z) - HyperNP: Interactive Visual Exploration of Multidimensional Projection
Hyperparameters [61.354362652006834]
HyperNP is a scalable method that allows for real-time interactive exploration of projection methods by training neural network approximations.
We evaluate the performance of the HyperNP across three datasets in terms of performance and speed.
arXiv Detail & Related papers (2021-06-25T17:28:14Z) - Online hyperparameter optimization by real-time recurrent learning [57.01871583756586]
Our framework takes advantage of the analogy between hyperparameter optimization and parameter learning in neural networks (RNNs)
It adapts a well-studied family of online learning algorithms for RNNs to tune hyperparameters and network parameters simultaneously.
This procedure yields systematically better generalization performance compared to standard methods, at a fraction of wallclock time.
arXiv Detail & Related papers (2021-02-15T19:36:18Z) - Automatic Setting of DNN Hyper-Parameters by Mixing Bayesian
Optimization and Tuning Rules [0.6875312133832078]
We build a new algorithm for evaluating and analyzing the results of the network on the training and validation sets.
We use a set of tuning rules to add new hyper-parameters and/or to reduce the hyper- parameter search space to select a better combination.
arXiv Detail & Related papers (2020-06-03T08:53:48Z) - Hyperparameter Selection for Subsampling Bootstraps [0.0]
A subsampling method like BLB serves as a powerful tool for assessing the quality of estimators for massive data.
The performance of the subsampling methods are highly influenced by the selection of tuning parameters.
We develop a hyperparameter selection methodology, which can be used to select tuning parameters for subsampling methods.
Both simulation studies and real data analysis demonstrate the superior advantage of our method.
arXiv Detail & Related papers (2020-06-02T17:10:45Z) - Automatic Hyper-Parameter Optimization Based on Mapping Discovery from
Data to Hyper-Parameters [3.37314595161109]
We propose an efficient automatic parameter optimization approach, which is based on the mapping from data to the corresponding hyper- parameters.
We show that the proposed approaches outperform the state-of-the-art apporaches significantly.
arXiv Detail & Related papers (2020-03-03T19:26:23Z)
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.