Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation

• URL: http://arxiv.org/abs/2110.10461v1
• Date: Wed, 20 Oct 2021 09:57:57 GMT
• Title: Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation
• Authors: Ross M. Clarke, Elre T. Oldewage, Jos\'e Miguel Hern\'andez-Lobato
• Abstract summary: We develop an approximate hypergradient-based hyper parameter optimiser. It requires only one training episode, with no restarts. We also provide a motivating argument for convergence to the true hypergradient.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning training methods depend plentifully and intricately on hyperparameters, motivating automated strategies for their optimisation. Many existing algorithms restart training for each new hyperparameter choice, at considerable computational cost. Some hypergradient-based one-pass methods exist, but these either cannot be applied to arbitrary optimiser hyperparameters (such as learning rates and momenta) or take several times longer to train than their base models. We extend these existing methods to develop an approximate hypergradient-based hyperparameter optimiser which is applicable to any continuous hyperparameter appearing in a differentiable model weight update, yet requires only one training episode, with no restarts. We also provide a motivating argument for convergence to the true hypergradient, and perform tractable gradient-based optimisation of independent learning rates for each model parameter. Our method performs competitively from varied random hyperparameter initialisations on several UCI datasets and Fashion-MNIST (using a one-layer MLP), Penn Treebank (using an LSTM) and CIFAR-10 (using a ResNet-18), in time only 2-3x greater than vanilla training.

Related papers

• Optimization Hyper-parameter Laws for Large Language Models [56.322914260197734]
  We present Opt-Laws, a framework that captures the relationship between hyper- parameters and training outcomes. Our validation across diverse model sizes and data scales demonstrates Opt-Laws' ability to accurately predict training loss. This approach significantly reduces computational costs while enhancing overall model performance.
  arXiv  Detail & Related papers  (2024-09-07T09:37:19Z)
• 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)
• Online Hyperparameter Optimization for Class-Incremental Learning [99.70569355681174]
  Class-incremental learning (CIL) aims to train a classification model while the number of classes increases phase-by-phase. An inherent challenge of CIL is the stability-plasticity tradeoff, i.e., CIL models should keep stable to retain old knowledge and keep plastic to absorb new knowledge. We propose an online learning method that can adaptively optimize the tradeoff without knowing the setting as a priori.
  arXiv  Detail & Related papers  (2023-01-11T17:58:51Z)
• Flatter, faster: scaling momentum for optimal speedup of SGD [0.0]
  We study training dynamics arising from interplay between gradient descent (SGD) and label noise and momentum in the training of neural networks. We find that scaling the momentum hyper parameter $1-NISTbeta$ with the learning rate to the power of $2/3$ maximally accelerates training, without sacrificing generalization.
  arXiv  Detail & Related papers  (2022-10-28T20:41:48Z)
• Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning [0.38073142980732994]
  Reinforcement learning is a promising paradigm for learning robot control, allowing complex control policies to be learned without requiring a dynamics model. We propose employing an ensemble of multiple reinforcement learning agents, each with a different set of hyper parameters, along with a mechanism for choosing the best performing set. Online weighted Q-Ensemble presented overall lower variance and superior results when compared with q-average ensembles.
  arXiv  Detail & Related papers  (2022-09-29T19:57:43Z)
• Online Hyperparameter Meta-Learning with Hypergradient Distillation [59.973770725729636]
  gradient-based meta-learning methods assume a set of parameters that do not participate in inner-optimization. We propose a novel HO method that can overcome these limitations, by approximating the second-order term with knowledge distillation.
  arXiv  Detail & Related papers  (2021-10-06T05:14:53Z)
• Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm [97.66038345864095]
  We propose a new hyperparameter optimization method with zeroth-order hyper-gradients (HOZOG) Specifically, we first formulate hyperparameter optimization as an A-based constrained optimization problem. Then, we use the average zeroth-order hyper-gradients to update hyper parameters.
  arXiv  Detail & Related papers  (2021-02-17T21:03:05Z)
• 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)
• HyperMorph: Amortized Hyperparameter Learning for Image Registration [8.13669868327082]
  HyperMorph is a learning-based strategy for deformable image registration. We show that it can be used to optimize multiple hyper parameters considerably faster than existing search strategies.
  arXiv  Detail & Related papers  (2021-01-04T15:39:16Z)
• Hippo: Taming Hyper-parameter Optimization of Deep Learning with Stage Trees [2.294014185517203]
  We propose Hippo, a hyper-parameter optimization system that removes redundancy in the training process to reduce the overall amount of computation significantly. Hippo is applicable to not only single studies, but multi-study scenarios as well, where multiple studies of the same model and search space can be formulated as trees of stages.
  arXiv  Detail & Related papers  (2020-06-22T02:36:12Z)
• Weighted Random Search for CNN Hyperparameter Optimization [0.0]
  We introduce the weighted Random Search (WRS) method, a combination of Random Search (RS) and probabilistic greedy. The criterion is the classification accuracy achieved within the same number of tested combinations of hyperparameter values. According to our experiments, the WRS algorithm outperforms the other methods.
  arXiv  Detail & Related papers  (2020-03-30T09:40:14Z)

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.