Enhancing accuracy of deep learning algorithms by training with low-discrepancy sequences

• URL: http://arxiv.org/abs/2005.12564v1
• Date: Tue, 26 May 2020 08:14:00 GMT
• Title: Enhancing accuracy of deep learning algorithms by training with low-discrepancy sequences
• Authors: Siddhartha Mishra, T. Konstantin Rusch
• Abstract summary: We propose a deep supervised learning algorithm based on low-discrepancy sequences as the training set. We demonstrate that the proposed algorithm significantly outperforms standard deep learning algorithms for problems in moderately high dimensions.
• Score: 15.2292571922932
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a deep supervised learning algorithm based on low-discrepancy sequences as the training set. By a combination of theoretical arguments and extensive numerical experiments we demonstrate that the proposed algorithm significantly outperforms standard deep learning algorithms that are based on randomly chosen training data, for problems in moderately high dimensions. The proposed algorithm provides an efficient method for building inexpensive surrogates for many underlying maps in the context of scientific computing.

Related papers

• Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL [106.82295532402335]
  Existing reinforcement learning algorithms suffer from computational intractability, strong statistical assumptions, and suboptimal sample complexity. We provide the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level. Our algorithm, MusIK, combines systematic exploration with representation learning based on multi-step inverse kinematics.
  arXiv  Detail & Related papers  (2023-04-12T14:51:47Z)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• Scalable computation of prediction intervals for neural networks via matrix sketching [79.44177623781043]
  Existing algorithms for uncertainty estimation require modifying the model architecture and training procedure. This work proposes a new algorithm that can be applied to a given trained neural network and produces approximate prediction intervals.
  arXiv  Detail & Related papers  (2022-05-06T13:18:31Z)
• Amortized Implicit Differentiation for Stochastic Bilevel Optimization [53.12363770169761]
  We study a class of algorithms for solving bilevel optimization problems in both deterministic and deterministic settings. We exploit a warm-start strategy to amortize the estimation of the exact gradient. By using this framework, our analysis shows these algorithms to match the computational complexity of methods that have access to an unbiased estimate of the gradient.
  arXiv  Detail & Related papers  (2021-11-29T15:10:09Z)
• Performance Analysis of Fractional Learning Algorithms [32.21539962359158]
  It is unclear whether the proclaimed superiority over conventional algorithms is well-grounded or is a myth as their performance has never been extensively analyzed. In this article, a rigorous analysis of fractional variants of the least mean squares and steepest descent algorithms is performed. Their origins and consequences on the performance of the learning algorithms are discussed and swift ready-witted remedies are proposed.
  arXiv  Detail & Related papers  (2021-10-11T12:06:44Z)
• Benchmarking Simulation-Based Inference [5.3898004059026325]
  Recent advances in probabilistic modelling have led to a large number of simulation-based inference algorithms which do not require numerical evaluation of likelihoods. We provide a benchmark with inference tasks and suitable performance metrics, with an initial selection of algorithms. We found that the choice of performance metric is critical, that even state-of-the-art algorithms have substantial room for improvement, and that sequential estimation improves sample efficiency.
  arXiv  Detail & Related papers  (2021-01-12T18:31:22Z)
• Evolving Reinforcement Learning Algorithms [186.62294652057062]
  We propose a method for meta-learning reinforcement learning algorithms. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. We highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games.
  arXiv  Detail & Related papers  (2021-01-08T18:55:07Z)
• Towards Optimally Efficient Tree Search with Deep Learning [76.64632985696237]
  This paper investigates the classical integer least-squares problem which estimates signals integer from linear models. The problem is NP-hard and often arises in diverse applications such as signal processing, bioinformatics, communications and machine learning. We propose a general hyper-accelerated tree search (HATS) algorithm by employing a deep neural network to estimate the optimal estimation for the underlying simplified memory-bounded A* algorithm.
  arXiv  Detail & Related papers  (2021-01-07T08:00:02Z)
• Accelerated learning algorithms of general fuzzy min-max neural network using a novel hyperbox selection rule [9.061408029414455]
  The paper proposes a method to accelerate the training process of a general fuzzy min-max neural network. The proposed approach is based on the mathematical formulas to form a branch-and-bound solution. The experimental results indicated the significant decrease in training time of the proposed approach for both online and agglomerative learning algorithms.
  arXiv  Detail & Related papers  (2020-03-25T11:26:18Z)
• Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation [2.4874453414078896]
  We provide a mathematically rigorous full error analysis of deep learning based empirical risk minimisation with quadratic loss function. We establish, however, the first full error analysis in the scientific literature for a deep learning based algorithm in the probabilistically strong sense.
  arXiv  Detail & Related papers  (2020-03-03T01:41:17Z)
• Boosting Algorithms for Estimating Optimal Individualized Treatment Rules [4.898659895355356]
  We present nonparametric algorithms for estimating optimal individualized treatment rules. The proposed algorithms are based on the XGBoost algorithm, which is known as one of the most powerful algorithms in the machine learning literature.
  arXiv  Detail & Related papers  (2020-01-31T22:26:38Z)

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.