#### Filter Results:

#### Publication Year

2012

2016

#### Co-author

#### Key Phrase

#### Publication Venue

Learn More

We study the stability properties of nonlinear multi-task regression in reproducing Hilbert spaces with operator-valued kernels. Such kernels, a.k.a. multi-task kernels, are appropriate for learning problems with nonscalar outputs like multi-task learning and structured output prediction. We show that multi-task kernel regression algorithms are uniformly… (More)

We consider the problem of learning a vector-valued function f in an online learning setting. The function f is assumed to lie in a reproducing Hilbert space of operator-valued kernels. We describe two online algorithms for learning f while taking into account the output structure. A first contribution is an algorithm, ONORMA, that extends the standard… (More)

- Julien Audiffren, Etienne Pardoux
- 2012

We consider the accumulation of deleterious mutations in an asexual population , a phenomenon known as Muller's ratchet, using the continuous time model proposed in [4]. We show that for any parameter λ > 0 (the rate at which mutations occur), for any α > 0 (the toxicity of the mutations) and for any size N > 0 of the population, the ratchet clicks a.s. in… (More)

A popular approach to apprenticeship learning (AL) is to formulate it as an inverse reinforcement learning (IRL) problem. The MaxEnt-IRL algorithm successfully integrates the maximum en-tropy principle into IRL and unlike its predecessors, it resolves the ambiguity arising from the fact that a possibly large number of policies could match the expert's… (More)

In this paper 1 we consider the problems of supervised classification and regression in the case where attributes and labels are functions: a data is represented by a set of functions, and the label is also a function. We focus on the use of reproducing kernel Hilbert space theory to learn from such functional data. Basic concepts and properties of… (More)

- Julien Audiffren
- 2012

We consider Muller's ratchet Fleming-Viot model with compensatory mutations , which is an infinite system of SDE used to study the accumulation of deleterious mutations in asexual population including mutations and selection. We construct a specific look-down model, and we prove that it is equivalent to the previous Muller's ratchet model.

One of the main challenges of deep learning methods is the choice of an appropriate training strategy. In particular, additional steps, such as unsupervised pre-training, have been shown to greatly improve the performances of deep structures. In this paper, we introduce a new training step,the post-training, which takes place after the training and where… (More)

- Julien Audiffren, Ralaivola Liva
- 2016

We adress the problem of dueling bandits defined on partially ordered sets, or posets. In this setting, arms may not be comparable, and there may be several (incomparable) optimal arms. We propose an algorithm, UnchainedBandits, that efficiently finds the set of optimal arms of any poset even when pairs of comparable arms cannot be distinguished from pairs… (More)

During the past few years, the Nintendo Wii Balance Board (WBB) has been used in postural control research as an affordable but less reliable replacement for laboratory grade force platforms. However, the WBB suffers some limitations, such as a lower accuracy and an inconsistent sampling rate. In this study, we focus on the latter, namely the non uniform… (More)

We adress the problem of dueling bandits defined on partially ordered sets, or posets. In this setting, arms may not be comparable, and there may be several (incomparable) optimal arms. We propose an algorithm, UnchainedBandits, that efficiently finds the set of optimal arms of any poset even when pairs of comparable arms cannot be distinguished from pairs… (More)