@GSAlberti profile picture
Giovanni S. Alberti @GSAlberti

Professor of Mathematical Analysis @malga_center, @UniGenova. Previously at ETH Zurich, École Normale Supérieure Paris, Oxford University.

Joined July 2012
  • Tweets 893
  • Following 307
  • Followers 385
66 Photos and videos
Giovanni S. Alberti retweeted
Matteo Santacesaria@matsanta
Jun 9
Diffusion models have a fundamental flaw: when trained on real-world noisy data, they just learn to perfectly generate that exact noise. We found a way to fix it. Introducing Manifold Attracted Diffusion (MAD), accepted at ICML 2026 🧵
1
1
2
129
📢 I’m happy to share that an interview about my research and academic journey has just been published in the @euromathsoc Magazine! This interview is part of a series in which @ERC_Research grantees are asked about their experiences and research. ems.press/journals/mag/artic…

Interview with Giovanni S. Alberti | EMS Press

Marie-Therese Wolfram, Marc Pfetsch

ems.press
1
2
107
We discussed various aspects of my work, with a special focus on my ERC project, as well as some broader reflections on applied mathematics and academic training. Many thanks to @mt_wolfram and Marc E. Pfetsch for a very engaging discussion!
83
I will give a talk on constraints for solutions to PDEs at the International Zoom Inverse Problems Seminar on 📅 Thursday 9th ⌚️ 6pm CEST, 12pm EDT, 9am PDT sites.uci.edu/inverse/
93
I am very happy to share that this work has just been published in SIAM Journal on Applied Mathematics! epubs.siam.org/eprint/EKHRVY…

The Learned Range Test Method for the Inverse Inclusion Problem | SIAM Journal on Applied Mathema...

Abstract. We consider the inverse problem consisting of the reconstruction of an inclusion contained in a bounded domain from a single pair of Cauchy data , where in and on . We show that the...

epubs.siam.org
Giovanni S. Alberti@GSAlberti
19 Nov 2024
New paper on #machinelearning for #inverseproblems: we show that sampling methods for inclusion detection are neural networks, and can be learned! Joint work with Shiwei Sun @malga_center, @UniGenova
6
243
New preprint "A convex lifting approach for the Calderón problem", by @GSAlberti, @rom1petit and @SimoneSanna1893
1
3
4
573
more replies
By lifting the product q(x)u(x) as a rank one operator, it is possible to write the inverse problem as a linear problem. We show that, if a non-degenerate source condition holds, the proposed convex problem has a unique solution that is the sought-after coefficient.
1
145
Paper: arxiv.org/abs/2507.00645 Funded by: @ERC_Research, @ItaliaDomaniGov, #INdAM

A convex lifting approach for the Calderón problem

The Calderón problem consists in recovering an unknown coefficient of a partial differential equation from boundary measurements of its solution. These measurements give rise to a highly...

arxiv.org
1
127
Very interesting training day for #erc grants at @LaStatale, thanks @ERC_Research @apre_it
6
180
Giovanni S. Alberti retweeted
Università di Genova@UniGenova
7 Mar 2025
MaLGa - Machine Learning Genoa Center ospita un seminario di @TomasoPoggio per ripercorrere le tappe fondamentali della ricerca sull'#intelligenzaartificiale da una prospettiva personale. 📌10 marzo 2025, ore 15:00, Genova ℹ️unige.it/news/tomaso-poggio-… #UniGe #UniGenova #TomasoPoggio

"Science of intelligence: a personal perspective", a MaLGa colloquium by Tomaso Poggio | UniGe |...

Il ciclo di seminari MaLGa Colloquia ospita Tomaso Poggio, una delle figure di riferimento nel campo dell'intelligenza artificiale e delle neuroscienze computazionali, per un intervento dal titolo...

unige.it
1
2
339
Giovanni S. Alberti retweeted
Matteo Santacesaria@matsanta
24 Dec 2024
🧵 Excited to share our new preprint on learning optimal regularizers for inverse problems! With @GSAlberti, EDeVito, THelin, MLassas, LRatti
1
1
3
369
Giovanni S. Alberti retweeted
arXiv math.FA Functional Analysis@mathFAbot
6 Jan 2025
Giovanni S. Alberti, Alessandro Felisi, Matteo Santacesaria, S. Ivan Trapasso: Compressed sensing for inverse problems II: applications to deconvolution, source recovery, and MRI arxiv.org/abs/2501.01929 arxiv.org/pdf/2501.01929
3
5
350
In effetti, un'intelligenza artificiale affidabile deve saper dire "Non lo so" arxiv.org/abs/2408.02357

On the consistent reasoning paradox of intelligence and optimal...

We introduce the Consistent Reasoning Paradox (CRP). Consistent reasoning, which lies at the core of human intelligence, is the ability to handle tasks that are equivalent, yet described by...

arxiv.org
Roberto Burioni@RobertoBurioni
4 Jan 2025
Replying to @RobertoBurioni
PS: ho fatto una cosa semplice, ho posto una domanda difficile a Grok. Mi ha risposto in modo errato, ma credibile. Ho detto che era sbagliato, ha fornito una seconda risposta credibileed errata. Una persona intelligente mi avrebbe risposto subito "non lo so".
2
154
Nice to be at @NYUAbuDhabi for the #AIMSConference2024 @AIM_Sciences
1
151
Talk on super-resolution in inverse scattering, with @rom1petit and @matsanta Slides: giovannisalberti.github.io/t… Funded by @ERC_Research @malga_center @UniGenova
2
5
254
Today I am giving an online talk on learning (simple) regularizers for inverse problems for the Data-Enabled Science Seminar, @UHouston 18:45 CET, 11:45 local time Slides: giovannisalberti.github.io/t…
1
104
Just to be clear
3
69
Giovanni S. Alberti retweeted
MaLGa@malga_center
5 Dec 2024
📅Today 5 PM 📍Accademia Ligure di Scienze e Lettere 🎙@AgneseSeminara @UniGenova "#AI to Decode Animal Behavior in Unpredictable Physical Environments" (Italian🇮🇹) explores how #reinforcementlearning helps understand how animals navigate turbulent environments using sensory cues
1
3
246
Load more