Sahra Ghalebikesabi
@SGhalebikesabi
Followers
2,497
Following
605
Media
7
Statuses
115
RS @GoogleDeepMind ; past: MSR PhD Fellow; @UniofOxford @oxcsml PhD on robustness, privacy and interpretability; intern @DeepMind @MSFTResearch
London, England
Joined May 2020
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
Texas
• 285633 Tweets
Yankees
• 251617 Tweets
WANG YIBO IN THE GT FINALS
• 155207 Tweets
Presiden
• 128396 Tweets
World Series
• 96947 Tweets
Juan Soto
• 65687 Tweets
期日前投票
• 60615 Tweets
HAPPY TWENTY FOURTH
• 47365 Tweets
#菊花賞
• 41510 Tweets
アーバンシック
• 39532 Tweets
ダノンデサイル
• 32424 Tweets
gerard
• 22702 Tweets
Happy Mashujaa
• 21235 Tweets
#虹7th_day2
• 21001 Tweets
Gowon
• 19710 Tweets
りんご飴
• 19348 Tweets
ダービー
• 16200 Tweets
#スパスタ3期
• 15094 Tweets
ねこあつめ2
• 14902 Tweets
メイショウタバル
• 14536 Tweets
コスモキュランダ
• 14465 Tweets
I have finally received my PhD from
@UniofOxford
@oxcsml
(and felt incredibly cool in the gown)!!
On a slightly belated note, I have been working as a Research Scientist on language models and privacy at
@GoogleDeepMind
. Stay tuned for the research from my amazing team 🥳🎉
108
76
3K
Thank you,
@MSFTResearch
!! I am so incredibly grateful and honoured to receive the MSR PhD Fellowship in Health Intelligence. A huge congratulations to the other recipients 🥳
Congratulations to our PhD fellowship recipients pursuing research in Health Intelligence at
@UniofOxford
,
@Penn
,
@UChicago
, and
@UM6P_officiel
.
2
7
17
10
3
122
My first oral!! Come around to Eindhoven at 4 pm today
@UncertaintyInAI
#UAI2022
. The stars of my talk: four different estimators of differentially private importance weights. I promise that at least one of them will make your synthetic data look more real!
0
4
62
This would have not been possible without the help of many and many people. For the purpose of tagging accounts with many followers, I want to thank
@StatMLIO
@OxfordStats
@Novartis
@MSFTResearch
and most importantly my supervisor
@cholmesuk
for supporting my studies.
2
0
34
It was such a pleasure to work with this amazing team. Are deep ensembles Bayesian or not?? Check out our paper to find out.
@vdwild
@SGhalebikesabi
@sejDino
and I rigorously connected Bayesian methods to deep ensembles using Wasserstein gradient flows!
Our results are summarised in a recent NeurIPS oral paper (), a 30-minute talk (), and below:
1
16
56
1
4
25
Proud to announce that we had \geq 0 people attending our AISTATS poster! We (
@rob_cornish
, Luke Kelly,
@cholmesuk
) bring back nonignorable missingness models, which were proposed by Little and Rubin in a time where neural networks were not as popular
2
0
21
Having been Publications Chair was fun! A big thank you to Neil for his support. And to the full committee for an amazing conference :)
#AISTATS2022
PMLR Volume 151
Proceedings of AISTATS 2022
Is now available:
1
7
48
1
0
19
It was an amazing experience to work with
@cholmesuk
, Edwin Fong and
@BrieucLehmann
on this new kind of Bayesian density estimation. If you’ve never heard of iterative Bayesian predictives, check out this thread.
#notAtISBA
📣 Preprint alert! 📣
Huge congrats to
@SGhalebikesabi
for this great piece of work 🎉
So, what is 'Density Estimation with Autoregressive Bayesian Predictives'...?
🧵/ 6
1
4
18
0
1
18
Have you ever been curious to know how your fancy NN behaves at a single prediction? Then check out our (
@TerLucile
*,
@karlado
,
@cholmesuk
) paper where we improve upon local explanation models (i.e. SHAP) by imposing a neighbourhood distribution as reference
3
8
17
Super excited to be Comms Chair with
@animesh_garg
for
@NeurIPSConf
this year! Mark the day, folks.
Call for Papers for
#Neurips2022
is out!
📅 May 19, 2022 1PM PDT
@SGhalebikesabi
& I will be Comms Chairs managing
@NeurIPSConf
among other things!
This is going to be a fun year!
3
9
84
0
1
16
@StatMLIO
@OxfordStats
@Novartis
@MSFTResearch
@cholmesuk
Credits to the amazing photographer and co-researcher
@jeanfrancois287
0
0
15
Do you work on foundation models?
➡️Submit to the
@NeurIPS2024
🍃MINT 2024: Workshop on Foundation Model Interventions
We feature a fantastic speaker lineup with
@AtticusGeiger
@hardmaru
@JacobSteinhardt
@viegasf
, space for discussions, and more!
2
6
14
🚨Have you ever wanted to attend a top-notch tutorial on explainable AI? 🚨
Not sure, I'll get there, but I will give it my best. Sign up here for the event hosted by
@QUANTESSLONDON
:
📅 Thursday, March 24 2022
🕧 6:00 pm UTC
1
4
12
Never again have the feeling that you wasted weeks working on a hypothesis you couldn’t support empirically. Just write it up in the next 1.5 months and submit it here:
Our CfP for our
@NeurIPSConf
workshop is officially out! Submit your negative results, summarised in 4-6 pages, until
*Sep 22, 2022*
#NeurIPS2022
Especially insightful negative results will be published in a special edition of PMLR.
0
8
18
0
2
9
Extremely grateful to be one of the Comms Chairs for
#NeurIPS2023
. If you’d like to help us organise the conference, nominate yourself here:
Planning is underway for
#NeurIPS2023
(New Orleans, Dec 10-16, 2023).
You can nominate organisers (incl. yourself) by Jan. 13. More details in our blog:
2
19
96
0
0
10
This would not have been possible without the constant support of my supervisor
@cholmesuk
, and the amazing mentorship I received from
@javiergonzh
. Lastly, thank you to my collaborator, Jack Jewson, for helping with the application!!
0
0
9
I had the pleasure to work closely with Olivia last year and can recommend any PhD student with experience in generative models to reach out to her!!!
Student researcher position applications are open at Google Deepmind!
I'm hosting a SR in the intersection of bias and generative models. If you're an interested PhD student please reach out!
…
0
21
49
0
0
7
I had the pleasure to intern with this truly amazing team and can only recommend applying :)
We have two opportunities to work at the intersection of machine learning and immunology as part of an amazing project
@MSFTResearch
and
@AdaptiveBiotech
.
2
14
69
0
0
7
A super cool event with amazing speakers for everyone interested in Privacy and Fairness in AI for Health!!
Curious about novel risks that AI introduces for patients and healthcare providers?
We're hosting an
#AIUK
Fringe event to explore Privacy and Fairness in AI for Health – Register now!
Date: 27 March, 10:00-16:30 GMT
Location:
@turinginst
, London
1/6
6
17
30
1
0
6
Think sustainable 🍃and re-cycle ♻️ ideas that didn’t work to make them useful to the community!! Stay tuned for the CfP.
🚀 Ever had a research idea that seemed brilliant but turned out to not work in practice? 🚀
Don’t move on to something else; your research has built a hypothesis and then disproved it! Present your work at our 🥳 now accepted 🥳 hybrid
@NeurIPSConf
workshop!
#NeurIPS2022
0
11
49
0
0
5
Proud office mate moments 🥰
@MenacherAnna
From Anna Menacher: A timeline of the most important statistical ideas of the past 50 years
1
23
73
0
0
4
Let your mind be blown away by Judy’s amazing research!!
Come check out my poster “On Measuring Private Model Disparities” at the AFCP workshop today! A sneak preview of my work from my summer internship! Yay!
4:20 pm
Room 392
#NeurIPS2022
1
5
152
0
0
4
We are creating a repo of negative results such that all beautiful ML ideas that did not work are easily searchable. If you know of a negative result tag
@ICBINBWorkshop
or fill out this form The more researchers engage, the more useful this becomes!
A yearly workshop is not enough to summarise all the beautiful ideas that did not work. So we are starting a *Repository of Negative Results*. Tag
@ICBINBWorkshop
whenever you see an idea that did not work, and we will add it to our Repo! Feedback welcomed
1
4
7
0
1
4
Shapley values explain the behaviour of a black box at a single prediction x by attributing each feature of the model with a numeric value. Roughly speaking, the Shapley value of feature j is the expected difference of the black box when evaluating it on an observation where ...
1
0
3
feature j takes value x_j and an observation where feature j was sampled from a pre-specified distribution. These distributions have so far been chosen globally, so we propose neighbourhood distributions that come with many nice properties!
0
0
3
Check out her great work on Weighted Likelihood Bootstraps here
Wonderful surprise: my work done at
@OxfordStats
on Posterior Bootstrap received the
#isba2021
Best Student/Postdoc Contributed Paper Award. Thank you
@ISBA_events
and everyone who was supporting me with this project!
#WomenInSTEM
3
4
61
1
0
2
@HarrisonDWilde
Yeah. I’ll be there!! I only registered on eventbrite. Is there anything else you would need to do
@AliShahinShams1
?
1
0
1