# O. Bousquet

Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

Learning with Local and Global Consistency

- Dengyong Zhou, O. Bousquet, T. N. Lal, J. Weston, B. Schölkopf
- Computer Science
- NIPS
- 9 December 2003

We consider the general problem of learning from labeled and unlabeled data, which is often called semi-supervised learning or transductive inference. A principled approach to semi-supervised… Expand

Stability and Generalization

- O. Bousquet, A. Elisseeff
- Computer Science, Mathematics
- J. Mach. Learn. Res.
- 1 March 2002

We define notions of stability for learning algorithms and show how to use these notions to derive generalization error bounds based on the empirical error and the leave-one-out error. The methods we… Expand

Measuring Statistical Dependence with Hilbert-Schmidt Norms

- A. Gretton, O. Bousquet, Alex Smola, B. Schölkopf
- Computer Science, Mathematics
- ALT
- 8 October 2005

We propose an independence criterion based on the eigen-spectrum of covariance operators in reproducing kernel Hilbert spaces (RKHSs), consisting of an empirical estimate of the Hilbert-Schmidt norm… Expand

Choosing Multiple Parameters for Support Vector Machines

- O. Chapelle, V. Vapnik, O. Bousquet, S. Mukherjee
- Mathematics, Computer Science
- Machine Learning
- 11 March 2002

The problem of automatically tuning multiple parameters for pattern recognition Support Vector Machines (SVMs) is considered. This is done by minimizing some estimates of the generalization error of… Expand

The Tradeoffs of Large Scale Learning

- L. Bottou, O. Bousquet
- Computer Science
- NIPS
- 3 December 2007

This contribution develops a theoretical framework that takes into account the effect of approximate optimization on learning algorithms. The analysis shows distinct tradeoffs for the case of… Expand

Local Rademacher complexities

- Peter L. Bartlett, O. Bousquet, S. Mendelson
- Mathematics
- 1 August 2005

We propose new bounds on the error of learning algorithms in terms of a data-dependent notion of complexity. The estimates we establish give optimal rates and are based on a local and empirical… Expand

Ranking on Data Manifolds

- Dengyong Zhou, J. Weston, A. Gretton, O. Bousquet, B. Schölkopf
- Computer Science
- NIPS
- 9 December 2003

The Google search engine has enjoyed huge success with its web page ranking algorithm, which exploits global, rather than local, hyperlink structure of the web using random walks. Here we propose a… Expand

Wasserstein Auto-Encoders

- I. Tolstikhin, O. Bousquet, S. Gelly, B. Schölkopf
- Computer Science, Mathematics
- ICLR
- 5 November 2017

We propose the Wasserstein Auto-Encoder (WAE)---a new algorithm for building a generative model of the data distribution. WAE minimizes a penalized form of the Wasserstein distance between the model… Expand

Are GANs Created Equal? A Large-Scale Study

- M. Lucic, Karol Kurach, M. Michalski, S. Gelly, O. Bousquet
- Computer Science, Mathematics
- NeurIPS
- 28 November 2017

Generative adversarial networks (GAN) are a powerful subclass of generative models. Despite a very rich research activity leading to numerous interesting GAN algorithms, it is still very hard to… Expand

A Bennett concentration inequality and its application to suprema of empirical processes

- O. Bousquet
- Mathematics, Economics
- 2002

We introduce new concentration inequalities for functions on product spaces They allow to obtain a Bennett type deviation bound for suprema of empirical processes indexed by upper bounded functions.… Expand