Alexandru Tifrea
@alexandrutifrea
Followers
204
Following
543
Media
5
Statuses
70
RT @AmartyaSanyal: Tomorrow in #AISTATS2025 , I'll present our poster on how label noise in training data and distribution shift in test do….
0
2
0
RT @AmartyaSanyal: Advertising an Open Postdoc position in learning theory/ privacy/ robustness/ unlearning or any related topics with me a….
0
3
0
RT @pdebartols: Landed in Singapore for #ICLR—excited to see old & new friends! I’ll be presenting:. 📌 RAMEN @ Main Conference on Saturday….
0
4
0
RT @AlizeePace: RL for real-world applications = offline learning + reward learning. How do we make this work?. Find out more at ICLR poste….
0
7
0
RT @AerniMichael: I'm also excited to present this paper about LLMs inadvertently leaking training data on Thursday….
0
2
0
RT @ramealexandre: Hiring two student researchers for Gemma post-training team at @GoogleDeepMind Paris! First topic is about diversity in….
0
36
0
Very excited about this tutorial at #AAAI2025 on inducing privacy, fairness or robustness to distribution shifts when data is imperfect (e.g. unlabeled, noisy)! You can check out the slides at
Very shortly at @RealAAAI , @alexandrutifrea and I will be giving a Tutorial on the impact of Quality and availability of labels and data for Privacy, Fairness, and Robustness of ML algorithms . See here @MLSectionUCPH @DIKU_Institut @GoogleDeepMind.
1
2
19
RT @ibomohsin: If you are interested in developing large-scale, multimodal datasets & benchmarks, and advancing AI through data-centric res….
0
4
0
RT @dmitrievdaniil7: We obtain information-theoretically optimal list size and recovery error, and provide empirical comparison with prior….
arxiv.org
We study the problem of estimating the means of well-separated mixtures when an adversary may add arbitrary outliers. While strong guarantees are available when the outlier fraction is...
0
2
0
RT @hamidpalangi: I am seeking student researchers to hire for 2025 focusing on Multi-Agent LLMs and Inference Time Decoding Algorithms. Id….
0
68
0
RT @AmartyaSanyal: Open Postdoctoral position in Privacy (and unlearning) and Robustness in Machine Learning in University of Copenhagen to….
0
41
0
RT @dmitrievdaniil7: Happy to present today at #ICML (1pm, Hall C 4-9, Poster 1508) our poster on deep random features networks with struct….
0
2
0
RT @AmartyaSanyal: With @yaxi_hu, we will present our work on Differential Privacy guarantees despite non-private preprocessing today in #I….
0
1
0
Come to the poster and check out the paper if you'd like to learn more! This is joint work with amazing collaborators at @GoogleDeepMind: @PreethiLahoti, @packer_ben, Yoni Halpern, @abeirami, and @FlavienProst.
arxiv.org
Despite achieving promising fairness-error trade-offs, in-processing mitigation techniques for group fairness cannot be employed in numerous practical applications with limited computation...
0
3
4
In the context of group fairness, we demonstrate how FRAPPÉ methods maintain the good performance of in-processing mitigations, at much lower computation and data costs. All this w/o requiring that sensitive attributes be known at prediction time! (unlike prior post-processing).
1
0
2
Excited to be at #ICML2024 to present on Thurs morning (11:30am, Hall C4-9, Poster 2217) our work on FRAPPÉ, a generic procedure for turning any multi-task objective into a modular bilevel optimization problem, with implications for fairness, alignment, or multi-domain learning.
2
4
29
RT @AmartyaSanyal: Led by @yaxi_hu, in collaboration with @bschoelkopf, we quantify the privacy degradation due to non-private preprocessi….
0
2
0
RT @AmartyaSanyal: The call for this position is now public. This will be jointly supervised with Prof. Amir Yehudayoff at @DIKU_Institut….
candidate.hr-manager.net
0
24
0
RT @AmartyaSanyal: I will soon be hiring another PhD student to work with me at @DIKU_Institut @MLSectionUCPH in topics related to. 1⃣ Trus….
0
10
0
RT @FannyYangETH: One step towards quantifying hidden confounding when multiple studies are available, joint work with my glorious students….
0
1
0