paper-with-me

홈 › Papers

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

2021-10-20 · ICLR 2022 4 · Ross M. Clarke, Elre T. Oldewage, José Miguel Hernández-Lobato

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.

📄 PDF Abstract BibTeX arXiv:2110.10461

Code (1)

rmclarke/optimisingweightupdatehyperparameters 공식 구현 pytorch

Similar Papers 제목 키워드 기반

High-Dimensional Bayesian Optimisation with Large-Scale Constraints -- An Application to Aeroelastic Tailoring

2023-12-14 · Hauke Maathuis, Roeland De Breuker, Saullo G. P. Castro

Design optimisation potentially leads to lightweight aircraft structures with lower environmental impact. Due to the high number of design variables and constraints, these problems are ordinarily solved using gradient-ba…

Bayesian OptimisationDimensionality Reduction

Portfolio optimisation with options

2021-11-24 · Jonathan Raimana Chan, Thomas Huckle, Antoine Jacquier, Aitor Muguruza

We develop a new analysis for portfolio optimisation with options, tackling the three fundamental issues with this problem: asymmetric options' distributions, high dimensionality and dependence structure. To do so, we pr…

MPLP: Learning a Message Passing Learning Protocol

2020-07-02 · Ettore Randazzo, Eyvind Niklasson, Alexander Mordvintsev

We present a novel method for learning the weights of an artificial neural network - a Message Passing Learning Protocol (MPLP). In MPLP, we abstract every operations occurring in ANNs as independent agents. Each agent i…

Wasserstein Robust Reinforcement Learning

2019-07-30 · Mohammed Amin Abdullah, Hang Ren, Haitham Bou Ammar, Vladimir Milenkovic 외

Reinforcement learning algorithms, though successful, tend to over-fit to training environments hampering their application to the real-world. This paper proposes $\text{W}\text{R}^{2}\text{L}$ -- a robust reinforcement …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

FuDoBa: Fusing Document and Knowledge Graph-based Representations with Bayesian Optimisation

2025-07-09 · Boshko Koloski, Senja Pollak, Roberto Navigli, Blaž Škrlj arxiv

Building on the success of Large Language Models (LLMs), LLM-based representations have dominated the document representation landscape, achieving great performance on the document embedding benchmarks. However, the high…

Representation Learning