Search Results for author: Roi Weiss

Found 9 papers, 1 papers with code

On Error and Compression Rates for Prototype Rules

no code implementations16 Jun 2022 Omer Kerem, Roi Weiss

We focus in particular on a close variant of a recently proposed compression-based learning rule termed OptiNet.

Tree density estimation

no code implementations23 Nov 2021 László Györfi, Aryeh Kontorovich, Roi Weiss

data we identify an optimal tree $T^*$ and efficiently construct a tree density estimate $f_n$ such that, without any regularity conditions on the density $f$, one has $\lim_{n\to \infty} \int |f_n(\boldsymbol x)-f_{T^*}(\boldsymbol x)|d\boldsymbol x=0$ a. s. For Lipschitz $f$ with bounded support, $\mathbb E \left\{ \int |f_n(\boldsymbol x)-f_{T^*}(\boldsymbol x)|d\boldsymbol x\right\}=O\big(n^{-1/4}\big)$, a dimension-free rate.

Density Estimation

Universal consistency and rates of convergence of multiclass prototype algorithms in metric spaces

no code implementations1 Oct 2020 László Györfi, Roi Weiss

We first obtain rates for the standard $k$-NN rule under a margin condition and a new generalized-Lipschitz condition.

Universal Bayes consistency in metric spaces

no code implementations24 Jun 2019 Steve Hanneke, Aryeh Kontorovich, Sivan Sabato, Roi Weiss

This is the first learning algorithm known to enjoy this property; by comparison, the $k$-NN classifier and its variants are not generally universally Bayes-consistent, except under additional structural assumptions, such as an inner product, a norm, finite dimension, or a Besicovitch-type property.

Learning Parametric-Output HMMs with Two Aliased States

no code implementations7 Feb 2015 Roi Weiss, Boaz Nadler

In various applications involving hidden Markov models (HMMs), some of the hidden states are aliased, having identical output distributions.

A Bayes consistent 1-NN classifier

no code implementations1 Jul 2014 Aryeh Kontorovich, Roi Weiss

We show that a simple modification of the 1-nearest neighbor classifier yields a strongly Bayes consistent learner.

Maximum Margin Multiclass Nearest Neighbors

no code implementations30 Jan 2014 Aryeh Kontorovich, Roi Weiss

We prove generalization bounds that match the state of the art in sample size $n$ and significantly improve the dependence on the number of classes $k$.

Generalization Bounds

Cannot find the paper you are looking for? You can Submit a new open access paper.