Nonparametric Compositional Stochastic Optimization for Risk-Sensitive Kernel Learning

نویسندگان

چکیده

In this work, we address optimization problems where the objective function is a nonlinear of an expected value, i.e., compositional stochastic programs. We consider case decision variable not vector-valued but instead belongs to Reproducing Kernel Hilbert Space (RKHS), motivated by risk-aware formulations supervised learning. develop first memory-efficient algorithm for setting, which call Compositional Online Learning with Kernels (COLK). COLK, at its core two time-scale approximation method, addresses facts that (i) compositions value cannot be addressed gradient method due presence inner expectation; and (ii) RKHS-induced parameterization has complexity proportional iteration index mitigated through greedily constructed subspace projections. provide, time, non-asymptotic tradeoff between required convergence accuracy both strongly convex non-convex objectives under constant step-sizes. Experiments risk-sensitive learning demonstrate COLK consistently converges performs reliably even when data full outliers, thus marks step towards overfitting. Specifically, observe favorable model complexity, consistent convergence, statistical associated heavy-tailed distributions.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Bayesian Nonparametric Kernel-Learning

Kernel methods are ubiquitous tools in machine learning. However, there is often little reason for the common practice of selecting a kernel a priori. Even if a universal approximating kernel is selected, the quality of the finite sample estimator may be greatly affected by the choice of kernel. Furthermore, when directly applying kernel methods, one typically needs to compute a N×N Gram matrix...

متن کامل

Hierarchically Compositional Kernels for Scalable Nonparametric Learning

We propose a novel class of kernels to alleviate the high computational cost of large-scale nonparametric learning with kernel methods. The proposed kernel is defined based on a hierarchical partitioning of the underlying data domain, where the Nyström method (a globally low-rank approximation) is married with a locally lossless approximation in a hierarchical fashion. The kernel maintains (str...

متن کامل

Stochastic Optimization for Kernel PCA

Kernel Principal Component Analysis (PCA) is a popular extension of PCA which is able to find nonlinear patterns from data. However, the application of kernel PCA to largescale problems remains a big challenge, due to its quadratic space complexity and cubic time complexity in the number of examples. To address this limitation, we utilize techniques from stochastic optimization to solve kernel ...

متن کامل

Nonparametric Regression Estimation under Kernel Polynomial Model for Unstructured Data

The nonparametric estimation(NE) of kernel polynomial regression (KPR) model is a powerful tool to visually depict the effect of covariates on response variable, when there exist unstructured and heterogeneous data. In this paper we introduce KPR model that is the mixture of nonparametric regression models with bootstrap algorithm, which is considered in a heterogeneous and unstructured framewo...

متن کامل

Structure Discovery in Nonparametric Regression through Compositional Kernel Search

Despite its importance, choosing the structural form of the kernel in nonparametric regression remains a black art. We define a space of kernel structures which are built compositionally by adding and multiplying a small number of base kernels. We present a method for searching over this space of structures which mirrors the scientific discovery process. The learned structures can often decompo...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Transactions on Signal Processing

سال: 2021

ISSN: ['1053-587X', '1941-0476']

DOI: https://doi.org/10.1109/tsp.2020.3046464