Variational Adaptive-Newton Method for Explorative Learning
نویسندگان
چکیده
We present the Variational Adaptive Newton (VAN) method which is a black-box optimization method especially suitable for explorativelearning 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.
منابع مشابه
A Regularized Nonsmooth Newton Method for Multi-class Support Vector Machines
Multi-class classification is an important and on-going research subject in machine learning. Recently, the ν-K-SVCR method was proposed by the authors for multi-class classification. Since many optimization problems have to be solved in multi-class classification, it is extremely important to develop an algorithm that can solve those optimization problems efficiently. In this paper, the optimi...
متن کاملVprop: Variational Inference using RMSprop
Many computationally-efficient methods for Bayesian deep learning rely on continuous optimization algorithms, but the implementation of these methods requires significant changes to existing code-bases. In this paper, we propose Vprop, a method for Gaussian variational inference that can be implemented with two minor changes to the off-the-shelf RMSprop optimizer. Vprop also reduces the memory ...
متن کاملRegularized nonsmooth Newton method for multi-class support vector machines
Multi-class classification is an important and on-going research subject in machine learning. Recently, the ν-K-SVCR method was proposed by the authors for multi-class classification. Since many optimization problems have to be solved in multi-class classification, it is extremely important to develop an algorithm that can solve those optimization problems efficiently. In this paper, the optimi...
متن کاملAn Adaptive Finite Element Approximation of a Variational Model of Brittle Fracture
Abstract. The energy of the Francfort–Marigo model of brittle fracture can be approximated, in the sense of Γ-convergence, by the Ambrosio–Tortorelli functional. In this work we formulate and analyze two adaptive finite element algorithms for the computation of its (local) minimizers. For each algorithm we combine a Newton-type method with residual-driven adaptive mesh refinement. We present tw...
متن کاملA Meshless Method for Variational Nonrigid 2-D Shape Registration
We present a method for nonrigid registration of 2-D geometric shapes. Our contribution is twofold. First, we extend the classic chamfer-matching energy to a variational functional. Secondly, we introduce a meshless deformation model that can adapt computation to the shape boundary. In our method, 2-D shapes are implicitly represented by a distance transform, and the registration error is defin...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1711.05560 شماره
صفحات -
تاریخ انتشار 2017