Publications related to Learning without Smoothness and Strong Convexity

Convex block-sparse linear regression with expanders - provably

Volkan Cevher, Quoc Tran Dinh, Anastasios Kyrillidis, Luca Baldassarre, Bubacarr Bah

Sparse matrices are favorable objects in machine learning and optimization. When such matrices are used, in place of dense ones, the overall complexity requirements in optimization can be significantly reduced in practice, both in terms of space and run-ti ...

2016

Fingerprinting the reactive toxicity pathways of 50 drinking water disinfection by-products

Urs von Gunten

A set of nine in vitro cellular bioassays indicative of different stages of the cellular toxicity pathway was applied to 50 disinfection by-products (DBPs) to obtain a better understanding of the commonalities and differences in the molecular mechanisms of ...

Elsevier2016

Fast rates by transferring from auxiliary hypotheses

Ilja Kuzborskij

In this work we consider the learning setting where, in addition to the training set, the learner receives a collection of auxiliary hypotheses originating from other tasks. We focus on a broad class of ERM-based linear algorithms that can be instantiated ...

2016

Designing Statistical Estimators That Balance Sample Size, Risk, and Computational Cost

Volkan Cevher

This paper proposes a tradeoff between computational time, sample complexity, and statistical accuracy that applies to statistical estimators based on convex optimization. When we have a large amount of data, we can exploit excess samples to decrease stati ...

Ieee-Inst Electrical Electronics Engineers Inc2015

A Geometric View on Constrained M-Estimators

Volkan Cevher, Yen-Huan Li, Ya-Ping Hsieh, Nissim Zerbib

We study the estimation error of constrained M-estimators, and derive explicit upper bounds on the expected estimation error determined by the Gaussian width of the constraint set. Both of the cases where the true parameter is on the boundary of the constr ...

2015

Locally Linear Neuro-Fuzzy Estimate of the Prosthetic Knee Angle and its Validation in a Robotic Simulator

Kamiar Aminian, Arash Arami, Natacha Vida Martins

Here we present a low-power magnetic measurement system based on only two Hall-effect elements and a permanent magnet integrated into a smart knee prosthesis to accurately measure knee flexion-extension. The smart prosthesis was tested in a robotic knee si ...

Institute of Electrical and Electronics Engineers2015

Process Design and Optimization (MLS-S03): a Journey in Modeling, Optimization and Regression

Julien Léo Billeter

This lecture describes the following topics: • Preamble on Linear Algebra • Dynamic and Static Models • Solving Dynamic and Static Models • Solving Optimization Problems • Solving Regression Problems ...

2015

Consistency of $\ell_1$-Regularized Maximum-Likelihood for Compressive Poisson Regression

Volkan Cevher, Yen-Huan Li

We consider Poisson regression with the canonical link function. This regression model is widely used in regression analysis involving count data; one important application in electrical engineering is transmission tomography. In this paper, we establish t ...

2015

Accuracy and Precision of Head Motion Information in Multi-Channel Free Induction Decay Navigators for Magnetic Resonance Imaging

Tobias Kober, Michael Herbst

Free induction decay (FID) navigators were found to qualitatively detect rigid-body head movements, yet it is unknown to what extent they can provide quantitative motion estimates. Here, we acquired FID navigators at different sampling rates and simultaneo ...

Ieee-Inst Electrical Electronics Engineers Inc2015

Sparsistency of $\ell_1$-Regularized $M$-Estimators

Volkan Cevher, Jonathan Mark Scarlett, Yen-Huan Li

We consider the model selection consistency or sparsistency of a broad set of

\ell_1

-regularized

M

-estimators for linear and non-linear statistical models in a unified fashion. For this purpose, we propose the local structured smoothness condition (LSS ...

2015

Learning without Smoothness and Strong Convexity

Graph Chatbot

Chat with Graph Search

Convex block-sparse linear regression with expanders - provably

Fingerprinting the reactive toxicity pathways of 50 drinking water disinfection by-products

Fast rates by transferring from auxiliary hypotheses

Designing Statistical Estimators That Balance Sample Size, Risk, and Computational Cost

A Geometric View on Constrained M-Estimators

Locally Linear Neuro-Fuzzy Estimate of the Prosthetic Knee Angle and its Validation in a Robotic Simulator

Process Design and Optimization (MLS-S03): a Journey in Modeling, Optimization and Regression

Consistency of $\ell_1$-Regularized Maximum-Likelihood for Compressive Poisson Regression

Accuracy and Precision of Head Motion Information in Multi-Channel Free Induction Decay Navigators for Magnetic Resonance Imaging

Sparsistency of $\ell_1$-Regularized $M$-Estimators

Process Design and Optimization (MLS-S03): a Journey in Modeling, Optimization and Regression

Designing Statistical Estimators That Balance Sample Size, Risk, and Computational Cost

Fingerprinting the reactive toxicity pathways of 50 drinking water disinfection by-products

A Geometric View on Constrained M-Estimators

Convex block-sparse linear regression with expanders - provably

Consistency of $\ell_1$-Regularized Maximum-Likelihood for Compressive Poisson Regression

Locally Linear Neuro-Fuzzy Estimate of the Prosthetic Knee Angle and its Validation in a Robotic Simulator

Fast rates by transferring from auxiliary hypotheses

Accuracy and Precision of Head Motion Information in Multi-Channel Free Induction Decay Navigators for Magnetic Resonance Imaging

Sparsistency of $\ell_1$-Regularized $M$-Estimators