António Góis

PhD student @Mila_Quebec; Interested in performative prediction, causality, evolution of cooperation,NLProc; prev @deep_spin @Unbabel HotClubeJazz @istecnico

[António Góis @AntGois]

@pmddomingos https://t.co/xXtPnzrPtH

[Pedro Domingos @pmddomingos]

Quantum computing breaks bitcoin, so if you own some your expected 5-year return is -100%.

[António Góis @AntGois]

.@eurowings Why is your support telling passengers "free seats don't exist" to force paid check-ins?

An agent told me I HAD to pay to finish check-in. I waited 20mins, tried the app again, and got a free seat easily. Stop using misleading sales pressure. #Eurowings #Travel

[Jose Gallego-Posada @JGallegoPosada]

Meet Cooper — a PyTorch library for constrained optimization in deep learning. 🚀

Cooper makes constraints as easy to use as losses!

@juan43ramirez @meraj_hashemi_ @SimonLacosteJ @Mila_Quebec

💻https://t.co/XU9BT3O63t

🧵👇

[Krikamol (Hiring Postdoc) @krikamol]

🥳 Just managed to finish the first draft of this work after almost four years of work 😅

(Im)possibility of Collective Intelligence
https://t.co/NF5ANPtFxo

Any feedback is highly appreciated 🙏

[António Góis @AntGois]

Check our poster tomorrow 3-6pm! @aistats_conf

[Simon Lacoste-Julien @SimonLacosteJ]

Check out this first paper on performative prediction with collective games at #AISTATS2025!

[Juan Ramirez @juan43ramirez]

Interested in NNs with improved tail performance?

Our #AISTATS2025 paper introduces Feasible Learning, a sample-centric learning paradigm that bounds per-sample losses!

@nachohounie @juaaan_e @JGallegoPosada @meraj_hashemi_ A. Ribeiro @SimonLacosteJ

https://t.co/saXfDRFFei

🧵

[ELLIS Unit Lisbon @Lisbon_ELLIS]

🚨Today is the last day to apply to the Lisbon Machine Learning School! Hear from top speakers in the field and get to meet new people during a fantastic week in Lisbon.

‼️Apply today: https://t.co/8VWqBsIxX9

[António Góis @AntGois]

Thank you to the HAIC organizers @iclr_conf ! Very friendly environment and interesting discussions today

@Mila_Quebec

[António Góis @AntGois]

Happy to announce "Performative Prediction on Games and Mechanism Design" was accepted at @aistats_conf 2025, and got spotlight at HAIC(@iclr_conf workshop)

with @mhrnz_m @fernandopsantos @gauthier_gidel @SimonLacosteJ (Mila and UvA)

https://t.co/u7PmINsjIm
Details below
1/9🧵

[António Góis @AntGois]

Tomorrow Sunday, 14h45! At @iclr_conf 2025 Workshop on Human-AI Coevolution (HAIC) @Mila_Quebec

[António Góis @AntGois]

Happy to announce "Performative Prediction on Games and Mechanism Design" was accepted at @aistats_conf 2025, and got spotlight at HAIC(@iclr_conf workshop)

with @mhrnz_m @fernandopsantos @gauthier_gidel @SimonLacosteJ (Mila and UvA)

https://t.co/u7PmINsjIm
Details below
1/9🧵

[Milad Aghajohari @MAghajohari]

Multi-Agent RL fails in real life. Agents cooperating to solve tasks remains a utopia.

-No scalable algorithms for general-sum games.
-In a simple apple-harvesting game, PPO agents overharvest and ruin bushes.

Advantage Alignment (ICLR 2025 Oral📢) is a huge step forward. 1/n

[António Góis @AntGois]

Feel free to reach out to chat about this work — either online or in-person at @iclr_conf and @aistats_conf
9/9🧵

[António Góis @AntGois]

Happy to announce "Performative Prediction on Games and Mechanism Design" was accepted at @aistats_conf 2025, and got spotlight at HAIC(@iclr_conf workshop)

with @mhrnz_m @fernandopsantos @gauthier_gidel @SimonLacosteJ (Mila and UvA)

https://t.co/u7PmINsjIm
Details below
1/9🧵

[António Góis @AntGois]

This connects to open questions in 𝗽𝗵𝗶𝗹𝗼𝘀𝗼𝗽𝗵𝘆 with practical relevance — how to evaluate performative models? Aiming for prosocial outcomes (appraisal view) undesirably injects moral values, endogenizing causes of adaptation (mitigation view) has side effects
8/9🧵

[Mario Figueiredo @mariotelfig]

Podem encontrar o meu comentário mais detalhado aqui: https://t.co/evXx9PQ1ts