paper-with-me

Papers

Nonparametric Online Learning Using Lipschitz Regularized Deep Neural Networks

2019-05-26 · Guy Uziel

Deep neural networks are considered to be state of the art models in many offline machine learning tasks. However, their performance and generalization abilities in online learning tasks are much less understood. Therefore, we focus on online learning and tackle the challenging problem where the underlying process is stationary and ergodic and thus removing the i.i.d. assumption and allowing observations to depend on each other arbitrarily. We prove the generalization abilities of Lipschitz regularized deep neural networks and show that by using those networks, a convergence to the best possible prediction strategy is guaranteed.

📄 PDF Abstract BibTeX arXiv:1905.10821

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Algorithmic Chaining and the Role of Partial Feedback in Online Nonparametric Learning

2017-02-27 · Nicolò Cesa-Bianchi, Pierre Gaillard, Claudio Gentile, Sébastien Gerchinovitz

We investigate contextual online learning with nonparametric (Lipschitz) comparison classes under different assumptions on losses and feedback information. For full information feedback and Lipschitz losses, we design th…

Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses

2020-10-22 · NeurIPS 2020 12 · Yihan Zhou, Victor S. Portella, Mark Schmidt, Nicholas J. A. Harvey

In online convex optimization (OCO), Lipschitz continuity of the functions is commonly assumed in order to obtain sublinear regret. Moreover, many algorithms have only logarithmic regret when these functions are also str…

Nonparametric Online Regression while Learning the Metric

2017-05-22 · NeurIPS 2017 12 · Ilja Kuzborskij, Nicolò Cesa-Bianchi

We study algorithms for online nonparametric regression that learn the directions along which the regression function is smoother. Our algorithm learns the Mahalanobis metric based on the gradient outer product matrix $\…

regression

Lazily Adapted Constant Kinky Inference for Nonparametric Regression and Model-Reference Adaptive Control

2016-12-31 · Jan-Peter Calliess

Techniques known as Nonlinear Set Membership prediction, Lipschitz Interpolation or Kinky Inference are approaches to machine learning that utilise presupposed Lipschitz properties to compute inferences over unobserved f…

BIG-bench Machine LearningGaussian Processesregression

Lipschitz Optimisation for Lipschitz Interpolation

2017-02-28 · Jan-Peter Calliess

Techniques known as Nonlinear Set Membership prediction, Kinky Inference or Lipschitz Interpolation are fast and numerically robust approaches to nonparametric machine learning that have been proposed to be utilised in t…

Prediction