`Travelled to:`

1 × Canada

1 × China

1 × France

1 × Germany

3 × USA

`Collaborated with:`

M.Marchand P.Germain S.Giguère A.Lacoste J.Roy A.Rolland H.Larochelle K.Sylla A.Habrard E.Morvant A.Lacasse S.Shanian

`Talks about:`

pac (5) classifi (3) bayesian (3) approach (3) learn (3) bound (3) bay (3) algorithm (2) compress (2) problem (2)

## Person: François Laviolette

### DBLP: Laviolette:Fran=ccedil=ois

### Contributed to:

### Wrote 8 papers:

- ICML-2015-GiguereRLM #algorithm #kernel #predict #problem #string
- Algorithms for the Hard Pre-Image Problem of String Kernels and the General Problem of String Prediction (SG, AR, FL, MM), pp. 2021–2029.
- ICML-c1-2014-LacosteMLL #learning
- Agnostic Bayesian Learning of Ensembles (AL, MM, FL, HL), pp. 611–619.
- ICML-c1-2013-GiguereLMS #algorithm #approach #bound #learning #predict
- Risk Bounds and Learning Algorithms for the Regression Approach to Structured Output Prediction (SG, FL, MM, KS), pp. 107–114.
- ICML-c3-2013-GermainHLM #adaptation #approach #classification #linear
- A PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers (PG, AH, FL, EM), pp. 738–746.
- ICML-2011-GermainLLMS #approach #kernel
- A PAC-Bayes Sample-compression Approach to Kernel Methods (PG, AL, FL, MM, SS), pp. 297–304.
- ICML-2011-RoyLM #bound #polynomial #source code
- From PAC-Bayes Bounds to Quadratic Programs for Majority Votes (JFR, FL, MM), pp. 649–656.
- ICML-2009-GermainLLM #classification #learning #linear
- PAC-Bayesian learning of linear classifiers (PG, AL, FL, MM), pp. 353–360.
- ICML-2005-LavioletteM #bound #classification
- PAC-Bayes risk bounds for sample-compressed Gibbs classifiers (FL, MM), pp. 481–488.