Publication

Stochastic Zeroth-Order Optimisation Algorithms with Variance Reduction

Related publications (40)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Excess-Risk of Distributed Stochastic Learners

Ali H. Sayed

This paper studies the learning ability of consensus and diffusion distributed learners from continuous streams of data arising from different but related statistical distributions. Four distinctive features for diffusion learners are revealed in relation ...

IEEE2016

Preconditioned Spectral Descent for Deep Learning

Volkan Cevher, Ya-Ping Hsieh, Edo Collins

Deep learning presents notorious computational challenges. These challenges in- clude, but are not limited to, the non-convexity of learning objectives and estimat- ing the quantities needed for optimization algorithms, such as gradients. While we do not a ...

2015

Accelerated And Inexact Forward-Backward Algorithms

Luca Baldassarre

We propose a convergence analysis of accelerated forward-backward splitting methods for composite function minimization, when the proximity operator is not available in closed form, and can only be computed up to a certain precision. We prove that the 1/k( ...

Siam Publications2013

Online performance guarantees for sparse recovery

Volkan Cevher

A K*-sparse vector x* ∈ RN produces measurements via linear dimensionality reduction as u = Φx* +n, where Φ ∈ RM×N (M

2011

Ensembles for sequence learning

Christos Dimitrakakis

This thesis explores the application of ensemble methods to sequential learning tasks. The focus is on the development and the critical examination of new methods or novel applications of existing methods, with emphasis on supervised and reinforcement lear ...

EPFL2007

Multivariate Calibration of Non-replicated Measurements for Heteroscedastic Errors

Nirav Pravinbhai Bhatt

The quality of multivariate calibration (MVC) models obtained depends on the effective treatment of errors in spectral data. If errors in different absorbance measurements are correlated and have different variances, then the Maximum Likelihood Principal C ...

2007

Network Loss Inference with Second Order Statistics of End-to-End Flows

Patrick Thiran, Xuan Hung Nguyen

We address the problem of calculating link loss rates from end-to-end measurements. Contrary to existing works that use only the average end-to-end loss rates or strict temporal correlations between probes, we exploit second-order moments of end-to-end flo ...

2007

Ensembles for Sequence Learning

Christos Dimitrakakis

École Polytechnique Fédérale de Lausanne2006

Influence and Change-of-Variance Functions of M-Quantiles

n this paper we compute the influence function and change-of-variance function of M-quantiles and deduce those of quantiles and expectiles as a special case. A redescending M-quantile constructed with Tukey's biweight is also studied. ...

1994

About the Change-of-Variance Function of M-Estimators of Scale

In this paper, we derive the correct change-of-variance function for M-estimators of scale under general contamination and apply it on two examples. Then we show that under quite general conditions B-robustness is an automatic by-product of V-robustness. ...

1993