paper-with-me

홈 › Papers

Variational Adaptive-Newton Method for Explorative Learning

2017-11-15 · Mohammad Emtiyaz Khan, Wu Lin, Voot Tangkaratt, Zuozhu Liu, Didrik Nielsen

We present the Variational Adaptive Newton (VAN) method which is a black-box optimization method especially suitable for explorative-learning tasks such as active learning and reinforcement learning. Similar to Bayesian methods, VAN estimates a distribution that can be used for exploration, but requires computations that are similar to continuous optimization methods. Our theoretical contribution reveals that VAN is a second-order method that unifies existing methods in distinct fields of continuous optimization, variational inference, and evolution strategies. Our experimental results show that VAN performs well on a wide-variety of learning tasks. This work presents a general-purpose explorative-learning method that has the potential to improve learning in areas such as active learning and reinforcement learning.

📄 PDF Abstract BibTeX arXiv:1711.05560

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Variational Inference

Similar Papers 제목 키워드 기반

Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions

2019-12-01 · NeurIPS 2019 12 · Peng Chen, Keyi Wu, Joshua Chen, Tom O'Leary-Roseberry 외

We propose a projected Stein variational Newton (pSVN) method for high-dimensional Bayesian inference. To address the curse of dimensionality, we exploit the intrinsic low-dimensional geometric structure of the posterior…

Bayesian Inference

Variational autoencoders for tissue heterogeneity exploration from (almost) no preprocessed mass spectrometry imaging data

2017-08-23 · Paolo Inglese, James L. Alexander, Anna Mroz, Zoltan Takats 외

The paper presents the application of Variational Autoencoders (VAE) for data dimensionality reduction and explorative analysis of mass spectrometry imaging data (MSI). The results confirm that VAEs are capable of detect…

Dimensionality Reduction

Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks

2020-07-21 · Alexander Immer

In this thesis, we disentangle the generalized Gauss-Newton and approximate inference for Bayesian deep learning. The generalized Gauss-Newton method is an optimization method that is used in several popular Bayesian dee…

Deep LearningGaussian Processes

Adaptive strategy in differential evolution via explicit exploitation and exploration controls

2020-02-03 · Sheng Xin Zhang, Wing Shing Chan, Kit Sang Tang, Shao Yong Zheng

Existing multi-strategy adaptive differential evolution (DE) commonly involves trials of multiple strategies and then rewards better-performing ones with more resources. However, the trials of an exploitative or explorat…

Evolutionary Algorithms

Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy

2016-05-24 · NeurIPS 2016 12 · Aryan Mokhtari, Alejandro Ribeiro

We consider empirical risk minimization for large-scale datasets. We introduce Ada Newton as an adaptive algorithm that uses Newton's method with adaptive sample sizes. The main idea of Ada Newton is to increase the size…