Aller au contenu

Aaron Roth

@aaroth.bsky.social did:plc:3q2kaxhjkceuc7kj4dmtfstl

Professor at Penn, Research Scientist at Resolution. Interested in machine learning, alignment, uncertainty quantification, game theory, privacy, fairness, and most of the intersections therein

Sur Bluesky depuis le

Abonnés
4 436
Abonnements
392
Posts
486
Jours dans les classements
0

Résumé

Aaron Roth (@aaroth.bsky.social) est sur Bluesky depuis le 20 octobre 2023. Le compte a 4 436 abonnés, suit 392 comptes et a publié 486 posts.

Présence dans les classements

Les meilleurs jours où les posts de ce compte sont entrés dans le top quotidien de Debya.

Ce compte n’est encore apparu dans aucun classement quotidien.

Posts aimés récemment

J’aime publics du réseau Bluesky.

  • Foundations of Responsible Computing@forcconf.bsky.social

    The #FORC2027 Call for Papers is up! Submit your best work on the foundations of responsible computing, including, e.g., privacy, robustness, fairness, and (for the first time!) safety and alignment! First deadline: November 11 Conf: June 2-4 at Stanford responsiblecomputing.org/forc-2027-ca...

    Voir le post
  • Gautam Kamath@gautamkamath.com

    I want to highlight 2 theorists who have distinguished themselves as true scholars: Sankeerth Rao Karingula & Shachar Lovett They have done exceptional work in simplifying and expositing recent breakthroughs on Komlos, 3SUM, etc. They have my highest respect.

    Voir le post
  • Thomas Dietterich@tdietterich.bsky.social

    ”Stochastic Parrot” was a derogatory intuition pump. It was intended to belittle LLM-based AI. This is not a mystery

    Voir le post
  • Zach Weinersmith@zachweinersmith.bsky.social

    I understand being amazed, bewildered, upset, horrified, excited, depressed, and many other things about this. I do not understand people saying it should be ignored or isn't real. I don't see how you can claim it doesn't matter without also claiming pure math doesn't matter.

    Voir le post
  • Rasmus Pagh@rasmuspagh.net

    The Gaussian mechanism is a key technique in differential privacy, used to make a bounded-sensitivity vector differentially privacy. Its analysis usually assumes the ability to perform computations with real numbers, so implementations must approximate the mechanism without breaking its guarantees.

    Voir le post

Connectez-vous pour en voir plus

Comptes bloqués

Sur Bluesky, les blocages sont publics.

Ce compte ne bloque personne.