🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I'm at #NeurIPS2022 this week! Come check out my poster for arxiv.org/abs/2202.05100 on Tuesday, 4pm-6pm Hall J #805 Reach out to chat about adaptivity, uncertainty, coffee, or music! Looking forward to finally putting an in-person face to some twitter handles and zoom screens

Interested in adaptivity, bandits, or causality? Come say hi today at #NeurIPS2022 4pm-6pm Hall J #805

Started my PhD with a pandemic, about to end it with a global recession. Is there a support group or something?

Celebrating #Statistics PhD Students for #WomenInScience in #Ontario: Emma Kroell, U of T Statistical Sciences 👤 emmakroell.ca Featured Work 📚 bit.ly/3YrSUqe More ℹ️ bit.ly/3xd5eOY #February11 #WomenInSTEM University of Toronto U of T Research U of T News U of T Arts & Science CANSSI - INCASS

Feature visualizations are widely used interpretability tools - but can we trust them? We investigate this question from an adversarial 🥷, empirical 🔬 and theoretical 📝 perspective. The result: Don’t trust your eyes! (1/6) Paper: arxiv.org/abs/2306.04719 🧵

3.5 years after we started this project while visiting Institute for Advanced Study (IAS), it’s been accepted to the Annals of Statistics. I won’t be at #JSM2023 but make sure to stop by Jeff’s session to hear about our work!

Many previous work of mine and others hinted ‘something fishy’ about saliency-based methods. But we never had a rigorous proof of what we saw. This work “Impossibility Theorems for Feature Attribution", now published in PNAS, to me marks a point of new beginnings.

Our recent PNAS paper shows that widely used interpretability methods, when used to ask simple counterfactual questions about models like “if I pay down this credit card will my credit score increase?”, are provably no better than random guessing. This is really problematic bc...

Join us next week (June 20) for the Theory of Interpretable AI seminar series, where Blair Bilodeau will discuss the ** fundamental theoretical limitations ** of attribution methods and its implications for interpretability! 🌐tverven.github.io/tiai-seminar/ Michal Moshkovitz Tim van Erven

You can’t take our country — and you can’t take our game.