G Grani

(she/they) Researcher @ Sapienza University of Rome. Interests: reinforcement learning, optimization, transport After 6pm: painting, photography, music, parties

[G Grani @Giulia_Grani]

Check out our newly published article "Solving the train dispatching problem via deep reinforcement learning", available online for a short period of time :)
https://t.co/dEdoDcf0V3

#Optrail #reinforcementlearning #rail #optimization #ai @ORMS_Elsevier

[G Grani @Giulia_Grani]

I am excited to announce that I will be organizing a special session on Distributed Computing in Bioinformatics and Computational Biology at the upcoming Conference on Computational Intelligence Methods for Bioinformatics & Biostatistics

https://t.co/Qjrq4IreeJ

[Yann LeCun @ylecun]

The great competition between Deep Learning frameworks enters a new phase.
Now that Google's TensorFlow has lost to Meta's PyTorch, Google is internally switching to JAX.

[Sergey Levine @svlevine]

NLP and offline RL are a perfect fit, enabling large language models to be trained to maximize rewards for tasks such as dialogue and text generation. We describe how ILQL can make this easy in our new paper: https://t.co/ssxXvihWit

Code: https://t.co/mrbFVX2Gar

Thread ->

[Ilya Sutskever @ilyasut]

the biggest lesson from deep learning is that you just gotta believe

[arXiv Daily @Arxiv_Daily]

Learning to solve Minimum Cost Multicuts efficiently using Edge-Weighted Graph Convolutional Neural Networks
https://t.co/JAnkdYkwIu
by Steffen Jung et al.
#LossFunction #ConvolutionalNeuralNetwork

[Google DeepMind @GoogleDeepMind]

Introducing #AlphaCode: a system that can compete at average human level in competitive coding competitions like @codeforces. An exciting leap in AI problem-solving capabilities, combining many advances in machine learning!

Read more: https://t.co/yaXfMWtEfe 1/

[G Grani @Giulia_Grani]

Check out the video! 🤩

[Cristina Molero del Río @crismolerorio]

You can now watch the recording of the sixth YOUNG #MachineLearning NeEDS #MathematicalOptimization session!!!

📹 https://t.co/Qg3XLw6qrj

👥 @Antonios93 from @unitorvergata
@GiorgioGrani from @SINTEFdigital

#orms @needs_project #riseneeds

[G Grani @Giulia_Grani]

Join us Dec 13 16:30 CET for this brilliant initiative

[Cristina Molero del Río @crismolerorio]

👇👇👇
The YOUNG🐥#MachineLearning NeEDS #MathematicalOptimization Online Seminar Series

➡️Dec 13, 16.30 CET
➡️3 speakers: @roinaveiro from @_ICMAT, @Antonios93 from @unitorvergata and @GiorgioGrani from @SINTEFdigital
➡️https://t.co/vgdOjlDYaO

#orms @needs_project #riseneeds

[Thiago Serra (@thserra.bsky.social) @thserra]

Did you know that some neural networks can be compressed without affecting their underlying models?

Some of the connections involved are at the 99th percentile of weight magnitude, all thanks to optimization! #orms

Come see our #NeurIPS2021 poster at 7:30 PM EST today!

[Martina Fischetti @MartiFischetti]

Are you a master student/a PhD/a PostDoc/a young researcher in #orms? Have you sign up for the 6th @AIROYoung workshop already? No? Hurry up! 😊 the workshop will be held in Rome (🍝☀️) on 23-25 of February. As always, free of charge!
Read more here: https://t.co/tsRihJi1v2

[Rishabh Agarwal @agarwl_]

[1/N] This work received an outstanding paper award at NeurIPS 2021!

To learn more about this work, please see https://t.co/RLOuconD1W. Some important links below.

[G Grani @Giulia_Grani]

@matteosalvinimi Compito a casa: “Il papà di Gesù è Giuseppe, Maria sua mamma e Dio suo Padre. Quanti genitori ha Gesù?”

ONORE ALLE ADDIZIONI

[Dolores Romero Morales @doloresromerom.bsky.social @DoloresRomeroM]

👇👇👇
#MachineLearning NeEDS #MathematicalOptimization Online Seminar Series

➡️ Prof Katya Scheinberg, from @Cornell
➡️ Stochastic Oracles and Where to Find Them
➡️ Nov 22, 17.30 CET
➡️ https://t.co/UsxAELFXN7

#orms @needs_project #riseneeds @EUROonline_News

[Google AI @GoogleAI]

Today we describe a collaboration with @TAE to improve fusion reactor performance by streamlining the optimization process, which helped to achieve longer stable plasma lifetimes, and we present research to better understand plasma behavior. Learn more at https://t.co/m7LHE5oapg

[Ashvin Nair @ashvinair]

A PyTorch re-implementation is now available - see https://t.co/xJADT3x13W

Use IQL for all your offline RL and online finetuning needs!

[G Grani @Giulia_Grani]

CPLEX was struggling this time!
@marta_monaci
#AI #optimization #Scheduling #orms #reinforcementlearning #machinelearning

[G Grani @Giulia_Grani]

CPLEX was struggling this time!
@marta_monaci
#AI #optimization #Scheduling #orms #reinforcementlearning #machinelearning

[arXiv math.OC Optimization and Control @mathOCb]

Marta Monaci, Valerio Agasucci, Giorgio Grani: An actor-critic algorithm with deep double recurrent agents to solve the job shop scheduling problem https://t.co/U4b9xntpFS https://t.co/A8Yf60XKEv

[G Grani @Giulia_Grani]

@JFPuget Look for tests

[Luca Fraccascia @LucaFraccascia]

Grazie a @ICESPItalia per aver diffuso la notizia del nostro #corso di #formazione su #economiacircolare e #sustainability #management a Sapienza Università di Roma, in collaborazione con @FondazioneCUOA

https://t.co/CnYv4LjLUa