A multi-objective perspective on jointly tuning hardware and hyperparameters

• URL: http://arxiv.org/abs/2106.05680v1
• Date: Thu, 10 Jun 2021 11:52:55 GMT
• Title: A multi-objective perspective on jointly tuning hardware and hyperparameters
• Authors: David Salinas, Valerio Perrone, Olivier Cruchant, Cedric Archambeau
• Abstract summary: A full AutoML solution requires selecting appropriate hardware automatically. We adopt a multi-objective approach that selects and adapts the hardware configuration automatically. We show in extensive NAS and HPO experiments that both ingredients bring significant speed-ups and cost savings.
• Score: 10.605719154114357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In addition to the best model architecture and hyperparameters, a full AutoML solution requires selecting appropriate hardware automatically. This can be framed as a multi-objective optimization problem: there is not a single best hardware configuration but a set of optimal ones achieving different trade-offs between cost and runtime. In practice, some choices may be overly costly or take days to train. To lift this burden, we adopt a multi-objective approach that selects and adapts the hardware configuration automatically alongside neural architectures and their hyperparameters. Our method builds on Hyperband and extends it in two ways. First, we replace the stopping rule used in Hyperband by a non-dominated sorting rule to preemptively stop unpromising configurations. Second, we leverage hyperparameter evaluations from related tasks via transfer learning by building a probabilistic estimate of the Pareto front that finds promising configurations more efficiently than random search. We show in extensive NAS and HPO experiments that both ingredients bring significant speed-ups and cost savings, with little to no impact on accuracy. In three benchmarks where hardware is selected in addition to hyperparameters, we obtain runtime and cost reductions of at least 5.8x and 8.8x, respectively. Furthermore, when applying our multi-objective method to the tuning of hyperparameters only, we obtain a 10\% improvement in runtime while maintaining the same accuracy on two popular NAS benchmarks.

Related papers

• Multi-objective Differentiable Neural Architecture Search [58.67218773054753]
  We propose a novel NAS algorithm that encodes user preferences for the trade-off between performance and hardware metrics. Our method outperforms existing MOO NAS methods across a broad range of qualitatively different search spaces and datasets.
  arXiv  Detail & Related papers  (2024-02-28T10:09:04Z)
• Parameter Optimization with Conscious Allocation (POCA) [4.478575931884855]
  Hyperband-based approaches to machine learning are among the most effective. We present. the new. Optimization with Conscious Allocation (POCA), a hyperband-based algorithm that adaptively allocates the inputted. budget to the hyperparameter configurations it generates. POCA finds strong configurations faster in both settings.
  arXiv  Detail & Related papers  (2023-12-29T00:13:55Z)
• Parallel Multi-Objective Hyperparameter Optimization with Uniform Normalization and Bounded Objectives [5.94867851915494]
  We propose a multi-objective Bayesian optimization (MoBO) algorithm that addresses these problems. We increase the efficiency of our approach by imposing constraints on the objective to avoid exploring unnecessary configurations. Finally, we leverage an approach to parallelize the MoBO which results in a 5x speed-up when using 16x more workers.
  arXiv  Detail & Related papers  (2023-09-26T13:48:04Z)
• Parameter-efficient Tuning of Large-scale Multimodal Foundation Model [68.24510810095802]
  We propose A graceful prompt framework for cross-modal transfer (Aurora) to overcome these challenges. Considering the redundancy in existing architectures, we first utilize the mode approximation to generate 0.1M trainable parameters to implement the multimodal prompt tuning. A thorough evaluation on six cross-modal benchmarks shows that it not only outperforms the state-of-the-art but even outperforms the full fine-tuning approach.
  arXiv  Detail & Related papers  (2023-05-15T06:40:56Z)
• Energy-efficient Task Adaptation for NLP Edge Inference Leveraging Heterogeneous Memory Architectures [68.91874045918112]
  adapter-ALBERT is an efficient model optimization for maximal data reuse across different tasks. We demonstrate the advantage of mapping the model to a heterogeneous on-chip memory architecture by performing simulations on a validated NLP edge accelerator.
  arXiv  Detail & Related papers  (2023-03-25T14:40:59Z)
• AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning [72.54359545547904]
  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$times$.
  arXiv  Detail & Related papers  (2022-03-15T19:25:01Z)
• A Comparative study of Hyper-Parameter Optimization Tools [2.6097538974670935]
  We compare the performance of four python libraries, namely Optuna, Hyperopt, Optunity, and sequential model algorithm configuration (SMAC) We found that Optuna has better performance for CASH problem and NeurIPS black-box optimization challenge.
  arXiv  Detail & Related papers  (2022-01-17T14:49:36Z)
• DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture [81.82173855071312]
  We propose an end-to-end solution that integrates the AutoML components and returns a ready-to-use model at the end of the search. Dha achieves state-of-the-art (SOTA) results on various datasets, especially 77.4% accuracy on ImageNet with cell based search space.
  arXiv  Detail & Related papers  (2021-09-13T08:12:50Z)
• Amortized Auto-Tuning: Cost-Efficient Transfer Optimization for Hyperparameter Recommendation [83.85021205445662]
  We propose an instantiation--amortized auto-tuning (AT2) to speed up tuning of machine learning models. We conduct a thorough analysis of the multi-task multi-fidelity Bayesian optimization framework, which leads to the best instantiation--amortized auto-tuning (AT2)
  arXiv  Detail & Related papers  (2021-06-17T00:01:18Z)
• 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)

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.