Vito Bellini

[Vito Bellini @vitobellini]

Our paper “A Unified Recommendation Model for Features Summarization” has been accepted at the 3rd @MuRS_WS, co-located with ACM #RecSys 2025 in Prague 🇨🇿!

🔗 Full paper here on Amazon Science: https://t.co/QpBpykS3bF

[Claudio Pomo @scne]

🤓🔍 Delve into the fascinating world of KGs and RecSys! Special thanks to our co-authors for their invaluable contributions to this research journey! 🚀🔗 @vitobellini #FrancescoDonini @DiSciascioEugen #AngeloSchiavone @azzurraragone (6/n)

[Vito Bellini @vitobellini]

@HarrieOos @Radboud_Uni Congratulations 🙌🏻

[Vito Bellini @vitobellini]

@iupdate Thanks god I didn’t buy it. Maybe I’ll wait for the 15. In the meanwhile my 11 pro still lasts a full day.

[Vito Bellini @vitobellini]

@commerzbank PhotoTAN funktioniert noch immer nicht und ich fahre am morgen in den Urlaub 😡

[Vito Bellini @vitobellini]

@elonmusk Civilization or economy?

[Vito Bellini @vitobellini]

@getorga @nicorsm But a beautiful one ☝️

[Vito Bellini @vitobellini]

Happy to share that both our papers have been accepted to The Web Conference 2022! @AmazonScience #amazonscience

Modeling position bias ranking for streaming media services
https://t.co/CjqnivYYrj

Fair effect attribution in parallel online experiments
https://t.co/y4drADUgaR

[Alexa @AmazonAlexa]

Let's make our planet a little greener. Celebrate #EarthDay with me by saying, “Alexa, grow a tree,” to donate $1 to plant a tree with One Tree Planted.

[Vito Bellini @vitobellini]

@elonmusk Let’s live in the real world, no need for authentications 🫢

[Vito Bellini @vitobellini]

@editingemily Why do you need to compare? Once you get the offer, if any, you can still decline it whether you don’t like the compensation :)

[Vito Bellini @vitobellini]

@Typora Discovered today. Life changer MD editor, simply the best! Finally very happy to edit tables in MD!

[Vito Bellini @vitobellini]

@culturedcode Hey guys, best app ever for to-dos list. Just one thing is missing: sharing notes with other Things users. Plan to implement it any time soon? Cheers!

[Mounia Lalmas @mounialalmas]

An excellent tutorial at #WSDM2021 on "Personalization in Practice". If you are working on personalization and recommender systems, this has lots of information on many aspects of #recsys. https://t.co/kcW8vIc6ON

[Vito Bellini @vitobellini]

@scne @Ryanair_IT E tu durante la pandemia vuoi viaggiare? A casa devi stare.

[Gabriel Peyré @gabrielpeyre]

The Levenberg-Marquardt is a standard method for non-linear least-squares, combining the best of gradient descent and Newton methods by replacing the Hessian by the Jacobian term only.
https://t.co/zQgk0X10XB

[Sergey Levine @svlevine]

Can we view RL as supervised learning, but where we also "optimize" the data? New blog post by Ben, Aviral, and Abhishek: https://t.co/8wZp0pEiOx

The idea: modify (reweight, resample, etc.) the data so that supervised regression onto actions produces better policies. More below:

[Yaroslav Bulatov @yaroslavvb]

What's the largest learning rate for which SGD converges? In deterministic case with Hessian H it is 2/||H||, from basic linear algebra. For SGD, an equivalent rate is 2/Tr(H), derivation from Russo-Dye theorem: https://t.co/XEvZYD0LK0

[Vito Bellini @vitobellini]

@hermesDE Hallo, mein Paket wurde gestern nicht geliefert, weil Sie die falsche Adresse geschrieben haben! Meine Sendungsnummer lautet 70153172700335. Der korrekte Straßenname lautet Rückertstrasse! Bitte hilf mir!