Skip to content

Commit 8eb3855

Browse files
author
Bastien Dussap
committed
New CV
1 parent 1d06548 commit 8eb3855

9 files changed

+119
-50
lines changed

‎assets/files/CV/CV-DussapBastien.aux

Lines changed: 11 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -20,15 +20,17 @@
2020
\babel@aux{english}{}
2121
\@writefile{toc}{\contentsline {section}{Education}{1}{section*.1}\protected@file@percent }
2222
\@writefile{toc}{\contentsline {section}{PhD thesis}{1}{section*.2}\protected@file@percent }
23-
\@writefile{toc}{\contentsline {section}{Experience}{1}{section*.3}\protected@file@percent }
24-
\@writefile{toc}{\contentsline {subsection}{Teaching}{1}{section*.4}\protected@file@percent }
25-
\@writefile{toc}{\contentsline {subsection}{Seminar}{1}{section*.5}\protected@file@percent }
23+
\@writefile{toc}{\contentsline {section}{Experience}{2}{section*.3}\protected@file@percent }
24+
\@writefile{toc}{\contentsline {subsection}{Teaching}{2}{section*.4}\protected@file@percent }
25+
\@writefile{toc}{\contentsline {subsection}{Seminar}{2}{section*.5}\protected@file@percent }
2626
\citation{*}
2727
\bibstyle{plain}
2828
\bibdata{publications}
29-
\@writefile{toc}{\contentsline {section}{Publication}{2}{section*.6}\protected@file@percent }
30-
\@writefile{toc}{\contentsline {section}{Award}{2}{section*.7}\protected@file@percent }
31-
\@writefile{toc}{\contentsline {section}{Languages}{2}{section*.8}\protected@file@percent }
32-
\@writefile{toc}{\contentsline {section}{Computer skills}{2}{section*.9}\protected@file@percent }
33-
\newlabel{lastpage}{{}{2}{}{section*.9}{}}
34-
\gdef \@abspage@last{2}
29+
\bibcite{dussap2023label}{1}
30+
\@writefile{toc}{\contentsline {section}{Publication}{3}{section*.6}\protected@file@percent }
31+
\@writefile{toc}{\contentsline {section}{Award}{3}{section*.7}\protected@file@percent }
32+
\@writefile{toc}{\contentsline {section}{Languages}{3}{section*.8}\protected@file@percent }
33+
\@writefile{toc}{\contentsline {section}{Computer skills}{3}{section*.9}\protected@file@percent }
34+
\@writefile{toc}{\contentsline {section}{References}{3}{section*.10}\protected@file@percent }
35+
\newlabel{lastpage}{{}{4}{}{section*.10}{}}
36+
\gdef \@abspage@last{4}

‎assets/files/CV/CV-DussapBastien.bbl

Lines changed: 9 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,9 @@
1+
\begin{thebibliography}{1}
2+
3+
\bibitem{dussap2023label}
4+
Bastien Dussap, Gilles Blanchard, and Badr-Eddine Ch{\'e}rief-Abdellatif.
5+
\newblock Label shift quantification with robustness guarantees via
6+
distribution feature matching.
7+
\newblock {\em arXiv preprint arXiv:2306.04376}, 2023.
8+
9+
\end{thebibliography}

‎assets/files/CV/CV-DussapBastien.blg

Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
1+
This is BibTeX, Version 0.99d (TeX Live 2022/dev/Debian)
2+
Capacity: max_strings=200000, hash_size=200000, hash_prime=170003
3+
The top-level auxiliary file: CV-DussapBastien.aux
4+
The style file: plain.bst
5+
Database file #1: publications.bib
6+
You've used 1 entry,
7+
2118 wiz_defined-function locations,
8+
502 strings with 4231 characters,
9+
and the built_in function-call counts, 291 in all, are:
10+
= -- 25
11+
> -- 18
12+
< -- 0
13+
+ -- 7
14+
- -- 6
15+
* -- 19
16+
:= -- 60
17+
add.period$ -- 3
18+
call.type$ -- 1
19+
change.case$ -- 6
20+
chr.to.int$ -- 0
21+
cite$ -- 1
22+
duplicate$ -- 10
23+
empty$ -- 18
24+
format.name$ -- 6
25+
if$ -- 54
26+
int.to.chr$ -- 0
27+
int.to.str$ -- 1
28+
missing$ -- 1
29+
newline$ -- 8
30+
num.names$ -- 2
31+
pop$ -- 6
32+
preamble$ -- 1
33+
purify$ -- 5
34+
quote$ -- 0
35+
skip$ -- 7
36+
stack$ -- 0
37+
substring$ -- 5
38+
swap$ -- 1
39+
text.length$ -- 0
40+
text.prefix$ -- 0
41+
top$ -- 0
42+
type$ -- 4
43+
warning$ -- 0
44+
while$ -- 2
45+
width$ -- 2
46+
write$ -- 12

‎assets/files/CV/CV-DussapBastien.log

Lines changed: 18 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
This is pdfTeX, Version 3.141592653-2.6-1.40.22 (TeX Live 2022/dev/Debian) (preloaded format=pdflatex 2023.6.8) 19 SEP 2023 14:53
1+
This is pdfTeX, Version 3.141592653-2.6-1.40.22 (TeX Live 2022/dev/Debian) (preloaded format=pdflatex 2024.3.15) 1 OCT 2024 15:54
22
entering extended mode
33
restricted \write18 enabled.
44
%&-line parsing enabled.
@@ -620,9 +620,9 @@ Language: english 2017/06/06 v3.3r English support from the babel system
620620
Package babel Info: Hyphen rules for 'canadian' set to \l@english
621621
(babel) (\language0). Reported on input line 102.
622622
Package babel Info: Hyphen rules for 'australian' set to \l@ukenglish
623-
(babel) (\language76). Reported on input line 105.
623+
(babel) (\language50). Reported on input line 105.
624624
Package babel Info: Hyphen rules for 'newzealand' set to \l@ukenglish
625-
(babel) (\language76). Reported on input line 108.
625+
(babel) (\language50). Reported on input line 108.
626626
))
627627
(/usr/share/texlive/texmf-dist/tex/latex/hyperref/hyperref.sty
628628
Package: hyperref 2021-06-07 v7.00m Hypertext links for LaTeX
@@ -950,27 +950,26 @@ LaTeX Font Info: External font `lmex10' loaded for size
950950
(Font) <6> on input line 94.
951951
[1
952952

953-
{/var/lib/texmf/fonts/map/pdftex/updmap/pdftex.map}]
954-
Overfull \hbox (0.79999pt too wide) in paragraph at lines 189--189
953+
{/var/lib/texmf/fonts/map/pdftex/updmap/pdftex.map}] [2]
954+
Overfull \hbox (0.79999pt too wide) in paragraph at lines 201--201
955955
[][]
956956
[]
957957

958958

959-
Overfull \hbox (1.81633pt too wide) in paragraph at lines 215--215
959+
Overfull \hbox (1.81633pt too wide) in paragraph at lines 227--227
960960
[]|\T1/lmr/m/n/10.95 (-20) Windows|
961961
[]
962962

963-
No file CV-DussapBastien.bbl.
964-
[2] (./CV-DussapBastien.aux)
963+
(./CV-DussapBastien.bbl [3]) [4] (./CV-DussapBastien.aux)
965964
Package rerunfilecheck Info: File `CV-DussapBastien.out' has not changed.
966-
(rerunfilecheck) Checksum: 765DC7F0E99DCD5274073E075B78AA8D;833.
965+
(rerunfilecheck) Checksum: A52F081D6ADDB2FBCE4F249548C2B397;928.
967966
)
968967
Here is how much of TeX's memory you used:
969-
27031 strings out of 478287
970-
520658 string characters out of 5849290
971-
855650 words of memory out of 5000000
972-
44636 multiletter control sequences out of 15000+600000
973-
541294 words of font info for 123 fonts, out of 8000000 for 9000
968+
27043 strings out of 478287
969+
520811 string characters out of 5849289
970+
856730 words of memory out of 5000000
971+
44640 multiletter control sequences out of 15000+600000
972+
541377 words of font info for 124 fonts, out of 8000000 for 9000
974973
1141 hyphenation exceptions out of 8191
975974
129i,12n,122p,1013b,582s stack positions out of 5000i,500n,10000p,200000b,80000s
976975
{/usr/share/texmf/fonts/enc/dvips/lm/lm-ec.enc}{/usr/share/texlive/texmf-dist
@@ -987,10 +986,10 @@ st/fonts/type1/public/fontawesome5/FontAwesome5Free-Solid.pfb></usr/share/texmf
987986
type1/public/lm/lmr17.pfb></usr/share/texmf/fonts/type1/public/lm/lmr8.pfb></us
988987
r/share/texmf/fonts/type1/public/lm/lmri10.pfb></usr/share/texmf/fonts/type1/pu
989988
blic/lm/lmro10.pfb></usr/share/texmf/fonts/type1/public/lm/lmro17.pfb>
990-
Output written on CV-DussapBastien.pdf (2 pages, 301310 bytes).
989+
Output written on CV-DussapBastien.pdf (4 pages, 306689 bytes).
991990
PDF statistics:
992-
139 PDF objects out of 1000 (max. 8388607)
993-
107 compressed objects within 2 object streams
994-
12 named destinations out of 1000 (max. 500000)
995-
38997 words of extra memory for PDF output out of 42996 (max. 10000000)
991+
155 PDF objects out of 1000 (max. 8388607)
992+
121 compressed objects within 2 object streams
993+
16 named destinations out of 1000 (max. 500000)
994+
39005 words of extra memory for PDF output out of 42996 (max. 10000000)
996995

‎assets/files/CV/CV-DussapBastien.out

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -7,3 +7,4 @@
77
\BOOKMARK [1][]{section*.7}{\376\377\000A\000w\000a\000r\000d}{}% 7
88
\BOOKMARK [1][]{section*.8}{\376\377\000L\000a\000n\000g\000u\000a\000g\000e\000s}{}% 8
99
\BOOKMARK [1][]{section*.9}{\376\377\000C\000o\000m\000p\000u\000t\000e\000r\000\040\000s\000k\000i\000l\000l\000s}{}% 9
10+
\BOOKMARK [1][]{section*.10}{\376\377\000R\000e\000f\000e\000r\000e\000n\000c\000e\000s}{}% 10

‎assets/files/CV/CV-DussapBastien.pdf

5.25 KB
Binary file not shown.

‎assets/files/CV/CV-DussapBastien.synctex.gz

4.13 KB
Binary file not shown.

‎assets/files/CV/CV-DussapBastien.tex

Lines changed: 31 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -40,14 +40,14 @@
4040
\usepackage[english]{babel} % FIXME: using spanish breaks moderncv
4141

4242
% personal data
43-
\name{Bastien}{Dussap}
44-
\title{PhD student in mathematics} % optional, remove / comment the line if not wanted
43+
\name{Bastien}{Dussap, phd}
44+
\title{Data Scientist} % optional, remove / comment the line if not wanted
4545
\born{17 June 1998} % optional, remove / comment the line if not wanted
4646
%\address{street and number}{postcode city}{country}% optional, remove / comment the line if not wanted; the "postcode city" and "country" arguments can be omitted or provided empty
4747
\phone[mobile]{07~77~99~21~57} % optional, remove / comment the line if not wanted; the optional "type" of the phone can be "mobile" (default), "fixed" or "fax"
4848
%\phone[fixed]{+2~(345)~678~901}
4949
%\phone[fax]{+3~(456)~789~012}
50-
\email{[email protected]} % optional, remove / comment the line if not wanted
50+
\email{[email protected]} % optional, remove / comment the line if not wanted
5151
\homepage{bastiendussap.github.io} % optional, remove / comment the line if not wanted
5252

5353
% Social icons
@@ -105,33 +105,45 @@ \section{Education}
105105
}
106106

107107
\section{PhD thesis}
108-
\cvitem{Title}{\emph{Cytometric data comparison}}
108+
\cvitem{Title}{\emph{A unified framework for label shift quantification}}
109109
\cvitem{Supervisors}{Gilles Blanchard and Marc Glisse}
110110
\cvitem{Abstract}{
111-
PhD thesis in partnership with Metafora biosystem a bio-engineering compary. The company has created a software, Metaflow, that allows automatic analysis of flow cytometry data. My work focuses on the use of machine learning models to transfer the analysis performed on one sample to a new unanalysed one. We rely on Reproducing Kernel Hilbert space to embed and store high-dimensional features in Euclidian Space. We use these representations to, firstly, estimate the proportions of each population in a new sample, and secondly to automatically name the cluster obtained by metaflow.
111+
In supervised classification, it is not uncommon that the information sought is not local, meaning the label associated to each data point, but global: obtaining the proportions of the different labels within the sample directly.
112+
This problem, which we have chosen to refer to as label shift quantification but which is also known by many other names in the literature, has seen a proliferation of publications since the mid-2000s.
113+
However, these works often proceed in parallel, coming from communities with limited dialogue, resulting in a scattered bibliography.
114+
In this manuscript, we first provide an overview of these diverse works with a twofold aim: first, to bridge the gap between these communities by presenting results from different research areas, and on the other hand, contextualise the subsequent work, particularly focusing on efforts to unify methods.
115+
Second, we propose a framework that unifies several classical methods from the literature based on mean vectorisations. We examine the theoretical guarantees of these methods and demonstrate their robustness when the central assumption of label shift is violated. We also extend this work by focusing on kernel-based vectorisations using covariance information rather than just the mean.
116+
Finally, we explore the use of a specific vectorisation based on Random Fourier Features in applications related to flow cytometry.
112117
}
113118

119+
\newpage
114120
\section{Experience}
115121
%\subsection{Vocational}
116122
%\cventry{year--year}{Job title}{Employer}{City}{}{General description no longer than 1--2 lines.\newline{}
117123
%Detailed achievements:
118124
%\begin{itemize}
119-
%\item Achievement 1
120-
%\item Achievement 2 (with sub-achievements)
121-
% \begin{itemize}
122-
% \item Sub-achievement (a);
123-
% \item Sub-achievement (b), with sub-sub-achievements (don't do this!);
124-
% \begin{itemize}
125-
% \item Sub-sub-achievement i;
126-
% \item Sub-sub-achievement ii;
127-
% \item Sub-sub-achievement iii;
128-
% \end{itemize}
129-
% \item Sub-achievement (c);
130-
% \end{itemize}
131-
%\item Achievement 3
132-
%\item Achievement 4
125+
%\item Achievement 1
126+
%\item Achievement 2 (with sub-achievements)
127+
% \begin{itemize}
128+
% \item Sub-achievement (a);
129+
% \item Sub-achievement (b), with sub-sub-achievements (don't do this!);
130+
% \begin{itemize}
131+
% \item Sub-sub-achievement i;
132+
% \item Sub-sub-achievement ii;
133+
% \item Sub-sub-achievement iii;
134+
% \end{itemize}
135+
% \item Sub-achievement (c);
136+
% \end{itemize}
137+
%\item Achievement 3
138+
%\item Achievement 4
133139
%\end{itemize}}
134140
%\cventry{year--year}{Job title}{Employer}{City}{}{Description line 1\newline{}Description line 2\newline{}Description line 3}
141+
142+
\cventry{2024--}{Data Scientist}{Metafora Biosystems}{}{}{
143+
Data Scientist at Metafora Biosystems.
144+
}
145+
146+
135147
\subsection{Teaching}
136148
\cventry{2022--2023}{Mathematics for Management}{IUT Sceaux}{L1 B.U.T GEA}{}{
137149
Taught by Patrick Pamphile.

‎index.md

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,15 @@
11
---
22
layout: page
33
title: Bastien Dussap
4-
subtitle: Researcher in applied mathematics at Paris Saclay University.
4+
subtitle: Data Scientist at Metafora Biosystems
55
---
66

77
# About me
88

9-
I am a PhD student in Machine Learning / Statistic at [University Paris-Saclay](https://www.universite-paris-saclay.fr/en) at the [institut de mathématiques d'orsay](https://www.imo.universite-paris-saclay.fr/fr/la-recherche/probabilites-et-statistiques/) under the supervision of [Gilles Blanchard](https://www.imo.universite-paris-saclay.fr/~gilles.blanchard/) and Marc Glisse. I'm also part of the [Datashape](https://team.inria.fr/datashape/) team (INRIA).
9+
Former PhD student in Machine Learning / Statistic at [University Paris-Saclay](https://www.universite-paris-saclay.fr/en) at the [institut de mathématiques d'orsay](https://www.imo.universite-paris-saclay.fr/fr/la-recherche/probabilites-et-statistiques/) under the supervision of [Gilles Blanchard](https://www.imo.universite-paris-saclay.fr/~gilles.blanchard/) and Marc Glisse. Was also part of the [Datashape](https://team.inria.fr/datashape/) team (INRIA).
1010
My thesis is in collaboration with [Metafora](https://www.metafora-biosystems.com/) a biotechnology company based at the Cochin Hospital.
1111

12-
My thesis deals with the comparison of cytometric datasets. Metafora has developped a software ([Metaflow](https://www.metafora-biosystems.com/metaflow/)), that allows automatic analysis of flow cytometry data. My work focuses on the use of machine learning models to transfer the analysis performed on one sample to a new unanalysed one. We rely on Reproducing Kernel Hilbert space to embed and store high-dimensional features in Euclidian Space. We use these representations to, firstly, estimate the proportions of each population in a new sample, and secondly to automatically name the cluster obtained by the software.
12+
My thesis dealt with the comparison of cytometric datasets. Metafora has developped a software ([Metaflow](https://www.metafora-biosystems.com/metaflow/)), that allows automatic analysis of flow cytometry data. My work focuses on the use of machine learning models to transfer the analysis performed on one sample to a new unanalysed one. We rely on Reproducing Kernel Hilbert space to embed and store high-dimensional features in Euclidian Space. We use these representations to, firstly, estimate the proportions of each population in a new sample, and secondly to automatically name the cluster obtained by the software.
1313

1414
## Research Interest
1515

0 commit comments

Comments
 (0)