Debabrota Basu

68 posts

Debabrota Basu

Debabrota Basu

@BasuDebabrota

Researcher. Writer. Robust, private, & ethical machine learning. Bandits, RL. Faculty @InriaScool in @Inria & @CNRS_HdF Teaching @ENS_ULM/@psl_univ, @univ_lille

France Katılım Şubat 2020
649 Takip Edilen176 Takipçiler
Sabitlenmiş Tweet
Debabrota Basu
Debabrota Basu@BasuDebabrota·
As bandits serve as the cornerstone of decision making with incomplete info & sequential interactions (e.g. recommenders), privacy becomes a pressing concern. We show #DifferentialPrivacy for (some) bandits is free. Is it true for contextual bandits also? #COLT2024 #openproblem
Scool@InriaScool

We've derived tight lower and upper bounds for differentially private finite-armed & linear bandits, while we lack the same for contextual bandits. At #COLT2024, @achraf_azize presents open problems in contextual bandits with privacy. @BasuDebabrota @Inria_Lille @RechercheUlille

English
0
1
9
386
Debabrota Basu
Debabrota Basu@BasuDebabrota·
It's fun to revisit the sanctum sanctorum: how does a brain learn? Today at Convention on Mathematics of #Neuroscience & #AI, @GuillaumeAP presents our work with @AdityaGilra on how to design a bio-plausible learning rule rather than backprop type methods to learn a time series.
Debabrota Basu tweet media
English
0
2
6
365
Debabrota Basu
Debabrota Basu@BasuDebabrota·
Yesterday, @achraf_azize presented @satml_conf the nuances of privacy definitions for bandits, information-theoretic lower bounds, and a wrapper to turn algorithms for linear, contextual, and multi-armed bandits "private". #differential_privacy #bandits 👉arxiv.org/pdf/2309.00557
Scool@InriaScool

1/2 To define privacy in bandits, we have to ask what are the input and output of a bandit algorithm? What differs if the adversary is interactive or passive? @achraf_azize & @BasuDebabrota address these in their work openreview.net/forum?id=2366a….

English
0
0
3
183
Debabrota Basu
Debabrota Basu@BasuDebabrota·
Check arxiv.org/pdf/2309.16563 & openreview.net/forum?id=oGIR0… to know more on regret bounds and algorithms for bandits with unbounded corruptions with light-and heavy-tailed rewards underneath. @InriaScool @Inria_Lille #Bandits #regret_bounds #ALT2024 @TmlrOrg
Scool@InriaScool

What happens in a bandit problem if epsilon fraction of feedback are arbitrarily corrupt? What are the new lower bounds on the regret? Can we design an optimal algorithm for #Bandits_corrupted_by_nature? We address this question in two parts.

English
0
0
5
187
Debabrota Basu retweetledi
Scool
Scool@InriaScool·
2/2 Can you reconstruct a million $ model just by querying it? Yes, you can replicate BERT's predictions with 90% efficacy only with 1k queries! At 5PM, @BasuDebabrota presents #Marich an information-theoretic unification of black-box model reconstruction: github.com/debabrota-basu…
Scool tweet media
English
0
1
3
157
Debabrota Basu
Debabrota Basu@BasuDebabrota·
As following up the interesting new works #EAAMO23, we would like to thank @ACMEAAMO for recognising our work on collective meritocracy and its impact on college admissions/candidate selection. 🙂 For more, check eaamo2022.eaamo.org/papers/buening… #EAAMO22 #FairML @Inria_Lille @InriaScool
ACM EAAMO (Handle Retired, Visit @EAAMO_ORG)@ACMEAAMO

The work of Thomas K. Buening, @MeiravSegal, @BasuDebabrota, @Annemage4FairAI and Christos Dimitrakakis was awarded in the same category. You can read it here: eaamo2022.eaamo.org/papers/buening… Congratulations! 🥳 Get inspired and register for #EAAMO23: cvent.me/lRbw7r (2/2)

English
0
1
4
495
Debabrota Basu
Debabrota Basu@BasuDebabrota·
Thanks to @IJCAIconf for the stage, & @bishwamittra & @ksmeel for the collaboration. Looking forward to discussions on algorithmic audit of ML/AI as a computational & interdisciplinary problem.🙏 #IJCAI2023 #AIaudit @univ_lille @Inria_Lille @InriaScool @NUSingapore @BenRbg
IJCAIconf@IJCAIconf

#Tutorial How do you choose your metric of bias? Debabrota Basu @BasuDebabrota @Inria kicking off the T16: Auditing Bias of Machine Learning Algorithms: Tools and Overview in tandem with Bishwamittra Ghosh @bishwamittra @astar_research #fairerAI #IJCAI2023 #formalmethods

English
0
1
8
1.1K
Debabrota Basu
Debabrota Basu@BasuDebabrota·
2/n With existing works & a demo, we address: 1. How to choose a fairness metric for an application? 2. How to measure bias of an ML algorithm given a fairness metric? 3. How to explain the measured bias as contributions of features? 👉 auditing-fairness-tutorial.github.io #AI_audit #FairML
Debabrota Basu tweet media
English
0
1
1
120
Debabrota Basu
Debabrota Basu@BasuDebabrota·
@ccanonne_ @UCSDJacobs @CambridgeUP Thanks for the book. 🙏 For last two years, we are studying bandits with Huber contamination model. We found the Huber book to be great for stats part. But a good reference for algorithmics was badly missing.
English
0
0
0
30
Mirco Mutti
Mirco Mutti@mirco_mutti·
Successfully defended my PhD thesis yesterday. I am grateful to my advisor Marcello, my brilliant co-authors, and all the mates at the lab in Milan. Looking forward to the next chapter!
Mirco Mutti tweet media
English
14
2
75
4.9K

Keşfet

@kohler_hector @GuillaumeAP @ImmanuelTrummer @Cornell @achraf_azize @satml_conf @InriaScool @Inria_Lille