Study of Diffusion Normalized Least Mean M-estimate Algorithms
- URL: http://arxiv.org/abs/2004.08998v1
- Date: Mon, 20 Apr 2020 00:28:41 GMT
- Title: Study of Diffusion Normalized Least Mean M-estimate Algorithms
- Authors: Y. Yu, H. He, T. Yang, X. Wang, R. C. de Lamare
- Abstract summary: This work proposes diffusion normalized least mean M-estimate algorithm based on the modified Huber function.
We analyze the transient, steady-state and stability behaviors of the algorithms in a unified framework.
Simulations in various impulsive noise scenarios show that the proposed algorithms are superior to some existing diffusion algorithms.
- Score: 0.8749675983608171
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This work proposes diffusion normalized least mean M-estimate algorithm based
on the modified Huber function, which can equip distributed networks with
robust learning capability in the presence of impulsive interference. In order
to exploit the system's underlying sparsity to further improve the learning
performance, a sparse-aware variant is also developed by incorporating the
$l_0$-norm of the estimates into the update process. We then analyze the
transient, steady-state and stability behaviors of the algorithms in a unified
framework. In particular, we present an analytical method that is simpler than
conventional approaches to deal with the score function since it removes the
requirements of integrals and Price's theorem. Simulations in various impulsive
noise scenarios show that the proposed algorithms are superior to some existing
diffusion algorithms and the theoretical results are verifiable.
Related papers
- On Policy Evaluation Algorithms in Distributional Reinforcement Learning [0.0]
We introduce a novel class of algorithms to efficiently approximate the unknown return distributions in policy evaluation problems from distributional reinforcement learning (DRL)
For a plain instance of our proposed class of algorithms we prove error bounds, both within Wasserstein and Kolmogorov--Smirnov distances.
For return distributions having probability density functions the algorithms yield approximations for these densities; error bounds are given within supremum norm.
arXiv Detail & Related papers (2024-07-19T10:06:01Z) - Observation-Guided Diffusion Probabilistic Models [41.749374023639156]
We propose a novel diffusion-based image generation method called the observation-guided diffusion probabilistic model (OGDM)
Our approach reestablishes the training objective by integrating the guidance of the observation process with the Markov chain.
We demonstrate the effectiveness of our training algorithm using diverse inference techniques on strong diffusion model baselines.
arXiv Detail & Related papers (2023-10-06T06:29:06Z) - Efficient Model-Free Exploration in Low-Rank MDPs [76.87340323826945]
Low-Rank Markov Decision Processes offer a simple, yet expressive framework for RL with function approximation.
Existing algorithms are either (1) computationally intractable, or (2) reliant upon restrictive statistical assumptions.
We propose the first provably sample-efficient algorithm for exploration in Low-Rank MDPs.
arXiv Detail & Related papers (2023-07-08T15:41:48Z) - Contraction-Guided Adaptive Partitioning for Reachability Analysis of
Neural Network Controlled Systems [5.359060261460183]
We present a contraction-guided adaptive partitioning algorithm for improving interval-valued reachable set estimates in a nonlinear feedback loop.
By leveraging a decoupling of the neural network verification step and reachability partitioning layers, the algorithm can provide accuracy improvements for little computational cost.
We report a sizable improvement in the accuracy of reachable set estimation in a fraction of the runtime as compared to state-of-the-art methods.
arXiv Detail & Related papers (2023-04-07T14:43:21Z) - 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) - Fractal Structure and Generalization Properties of Stochastic
Optimization Algorithms [71.62575565990502]
We prove that the generalization error of an optimization algorithm can be bounded on the complexity' of the fractal structure that underlies its generalization measure.
We further specialize our results to specific problems (e.g., linear/logistic regression, one hidden/layered neural networks) and algorithms.
arXiv Detail & Related papers (2021-06-09T08:05:36Z) - Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via
Online High-Confidence Change-Point Detection [7.685002911021767]
We introduce an algorithm that efficiently learns policies in non-stationary environments.
It analyzes a possibly infinite stream of data and computes, in real-time, high-confidence change-point detection statistics.
We show that (i) this algorithm minimizes the delay until unforeseen changes to a context are detected, thereby allowing for rapid responses.
arXiv Detail & Related papers (2021-05-20T01:57:52Z) - Reparameterized Variational Divergence Minimization for Stable Imitation [57.06909373038396]
We study the extent to which variations in the choice of probabilistic divergence may yield more performant ILO algorithms.
We contribute a re parameterization trick for adversarial imitation learning to alleviate the challenges of the promising $f$-divergence minimization framework.
Empirically, we demonstrate that our design choices allow for ILO algorithms that outperform baseline approaches and more closely match expert performance in low-dimensional continuous-control tasks.
arXiv Detail & Related papers (2020-06-18T19:04:09Z) - Communication-Efficient Distributed Stochastic AUC Maximization with
Deep Neural Networks [50.42141893913188]
We study a distributed variable for large-scale AUC for a neural network as with a deep neural network.
Our model requires a much less number of communication rounds and still a number of communication rounds in theory.
Our experiments on several datasets show the effectiveness of our theory and also confirm our theory.
arXiv Detail & Related papers (2020-05-05T18:08:23Z) - A Distributional Analysis of Sampling-Based Reinforcement Learning
Algorithms [67.67377846416106]
We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes.
We show that value-based methods such as TD($lambda$) and $Q$-Learning have update rules which are contractive in the space of distributions of functions.
arXiv Detail & Related papers (2020-03-27T05:13:29Z)
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.