Latest News:
2021-09-28
2021-06-05
2021-05-08
2020-08-09
2019-05-10
2019-04-20
2019-02-01
2018-12-18
2018-12-07
2018-03-23
2017-10-24
2017-09-06
2017-03-02
2016-08-15
2016-04-06
2016-03-05
2016-01-14
Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound has been accepted at NeurIPS 2021
2021-06-05
excited to mentor FDL-Europe's on-board ML challenge this summer!
2021-05-08
Learning Binary Trees by Argmin Differentiation was accepted at ICML 2021
2020-08-09
I am speaking at the AI and Space panel at WAI global submit
2019-05-10
excited to join the FDL-Europe this summer!
2019-04-20
I was awarded with the "Prix de Thèse" from the French Society for AI
2019-02-01
I was awarded with the "Prix Excellence Doctorat" from the Université Jean Monnet
2018-12-18
I defended my PhD thesis, entitled "A unified view of local learning: theory and algorithms for enhancing linear models"
2018-12-07
"Communication-Efficient Decentralized Boosting while Discovering the Collaboration Graph" presented at MLPCD 2 NeurIPS Workshop
2018-03-23
Adversarial Robustness Toolbox is now available on github
2017-10-24
2017-09-06
our work on adversarial examples will be presented at AISec2017
2017-03-02
the paper L3SVMs, co-written with R.Emonet and M.Sebban, is now available on arxiv
2016-08-15
2016-04-06
the paper Lipschitz Continuity of Mahalanobis Distances and Bilinear Forms, co-written with R.Emonet and M.Sebban, is now available on arxiv
2016-03-05
2016-01-14
talk on c2lm at Lives ANR project kick-off at Univ. Marseille
Publications
- 2021 Zantedeschi, Viallard, Morvant, Emonet, Habrard, Germain, Guedj
Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
paper
accepted at NeurIPS 2021 for publication
- 2020 Valentina Zantedeschi, Matt Kusner, Vlad Niculae
Learning Binary Trees by Argmin Differentiation
paper
accepted at ICML 2021 for publication
- 2020 Schroeder de Witt, Tong, Zantedeschi, De Martini, Kalaitzis, Chantry, Watson-Parris, Bilinski
RainBench: Towards Global Precipitation Forecasting from Satellite Imagery
paper
accepted at AAAI 2021 for publication
- 2020 Zantedeschi, De Martini, Tong, Schroeder de Witt, Kalaitzis, Bilinski, Chantry, Watson-Parris
Towards Data-Driven Physics-Informed Global Precipitation Forecasting from Satellite Imagery
paper
accepted at AI4 Earth Sciences and CCAI, NeurIPS 2020 Workshops
- 2019 Zantedeschi, Falasca, Douglas, Strange, Kusner, Watson-Parris
CUMULO: A Dataset for Learning Cloud Classes
paper, dataset, code, slides, talk, poster
Best paper award at NeurIPS 2019 Workshop, Tackling Climate Change with Machine Learning
- 2019 Gautheron, Germain, Habrard, Letarte, Morvant, Sebban, Zantedeschi
PAC-Bayes Approaches to Landmark-Based Learning with Random Fourier Features
paper, code
accepted at ECML 2020 for publication
- 2019 Valentina Zantedeschi, Aurélien Bellet, Marc Tommasi
Communication-Efficient and Decentralized Multi-Task Boosting while Learning the Collaboration Graph
paper, code
accepted at AISTATS 2020 for publication
- 2018 PhD Dissertation
A unified view of local learning: theory and algorithms for enhancing linear models
manuscript, slides
Best PhD dissertation award from French Society for AI
- 2018 Valentina Zantedeschi, Rémi Emonet, Marc Sebban
Fast and Provably Effective Multi-view Classification with Landmark-based SVM
paper, BibTex
accepted at ECML 2018 for publication
- 2017 Valentina Zantedeschi, Maria-Irina Nicolae, Ambrish Rawat
Efficient Defenses against Adversarial Attacks
paper, BibTex, slides, talk
presented at AISEC 2017 and Grehack 2017
- 2017 Valentina Zantedeschi, Rémi Emonet, Marc Sebban
L3SVMs: Landmarks-based Linear Local Support Vectors Machines
site
- 2016 Valentina Zantedeschi, Rémi Emonet, Marc Sebban
beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data
site
accepted at NIPS 2016 for publication
- 2016 Valentina Zantedeschi, Rémi Emonet, Marc Sebban
Metric Learning as Convex Combination of Local Models with Generalization Guarantees
site
accepted at CVPR 2016 for publication
- 2016 Valentina Zantedeschi, Rémi Emonet, Marc Sebban
Lipschitz Continuity of Mahalanobis Distances and Bilinear Forms
arxiv, BibTex
Research Experience
- Summer 2020
Research Scientist at Frontier Development Lab, Europe
Data-driven global precipitation forecasting - Summer 2019
Research Scientist at Frontier Development Lab, Europe, mentored by Matt Kusner and Duncan Watson-Parris
Atmospheric Phenomena and Climate Variability challenge - September 2017
Research Visit at INRIA, Lille, collaborating with Marc Tommasi and Aurélien Bellet
decentralized learning of personalized models exploiting information of a graph of users - May-August 2017
Research Internship at IBM Research, Dublin, supervised by Mathieu Sinn and Maria-Irina Nicolae
studying and building Deep Learning architectures robust to adversarial examples - Avril-September 2015 MSc Thesis at Lab. H.Curien, Saint-Etienne, supervised by R.Emonet and M.Sebban
Local Metrics learning and combination for color distance estimation - May-September 2014 Master Internship at Lab. H.Curien, Saint-Etienne, supervised by R.Emonet and M.Sebban
Fisher Kernels in temporal probabilistic models for classification