🚨 New Preprint Alert! 🚨
Are you interested in Imprecise Probability (IP)? Then check out our latest preprint "Truthful Elicitation of Imprecise Forecasts". Joint work with @Chau9991 and @krikamol.
https://t.co/pzpPEe1UOh
A quick thread🧵(1/3)
Remember how we never really solved adversarial examples on CIFAR-10 and said this was a makeup toy problem that didn't matter?
Turns out the fundamental ideas that prevent test time example manipulation attacks are kinda important now.
@SarveshGharat12@aryehazan Yes, the probability is greater than equal to 0. I don't think you can have a uniform non trivial lower bound for any unknown distribution because we don't control the support and it may be such that there is no support for point we want to lower bound the random variable with
🚨I’m more than happy to share our new work:
A critical question for any second order uncertainty quantification is to ask “even if valid, what to do with it?”. Our answer is this work! We offer coverage guarantee per input, and return sets that are optimally efficient.
🧠 How do we compare uncertainties that are themselves imprecisely specified?
💡Meet IIPM (Integral IMPRECISE probability metrics) and MMI (Maximum Mean IMPRECISION): frameworks to compare and quantify Epistemic Uncertainty!
With the amazing @mic_caprio and @krikamol 🚀
🚨 🇪🇺 Seeking a postdoc opportunity under the 2025 call for the Marie Sklodowska-Curie Actions (MSCA 2025) Postdoctoral Fellowships?
😎 Come work with the Rational Intelligence Lab at CISPA in Saarbrücken, Germany.
🔗 https://t.co/kRtFXc8DQo
RT Please 🙏
@DimitrisPapail@abeirami A small plug. Perhaps our take on generalisation in our ICML 24 spotlight paper can shed some light.
We say normatively OOD is based on the idea of subjective loss or belief probability during deployment.
https://t.co/c4xw71m9S0
🎉Thrilled to share that our paper “Truthful Elicitation of Imprecise Forecasts” has been accepted as an Oral presentation at #UAI2025! 🙌
Check it out: https://t.co/RBJBEsB5Va
@_anurags14@krikamol
@ShashwatGoel7 I also strongly believe that this delta created in the high school transfers to the delta in the higher education in universities across Delhi with all these students joining there. Resulting in one of the highest concentration of high quality talent in India.
(3/3)
For a long time, the IP community has believed that a strictly proper scoring rule for IP is impossible. While true, the impossibility is only for deterministic rules! Our results propose a randomized strictly proper rule for IP. Check out our preprint for more details!
🚨 New Preprint Alert! 🚨
Are you interested in Imprecise Probability (IP)? Then check out our latest preprint "Truthful Elicitation of Imprecise Forecasts". Joint work with @Chau9991 and @krikamol.
https://t.co/pzpPEe1UOh
A quick thread🧵(1/3)
(2/3)
Apart from Bayes' Rule, strictly proper scoring rules are another fundamental component of the Bayesian perspective. They provide the correct incentives for truthful probabilistic reporting, called Truthful Elicitation. Our Motivation: Can we do something similar for IP?
I am at @icml2024 with @_anurags14 and @krikamol to present our spotlight work on domain generalisation via imprecise learning this week!
Come and have a discussion if you are interested in uncertainty-aware ML, explainability, and preference modelling!
#ICML2024
✈️ I’ll be at @icmlconf next week together with @Chau9991 and @_anurags14 to present our work on imprecise generalization. Looking forward to catching up with everyone.
#ICML2024
@CISPA@Chau9991@krikamol Of course, if you want to read a bit more technical stuff, you can refer to another blog that contains a technical introduction. In case you are in-person at ICML, drop by our spotlight presentation on Thursday from 11:30 AM :D
https://t.co/e7stCN8zI5
AI industry is giving a huge push to AI Alignment. For example, Open AI below. In my discussions with ML researchers in academia, I hear too much pessimism about being GPU-poor. I want to discuss what academia can contribute to this field! 🧵(1/n)
https://t.co/Gcn4rtlFTn