#DellaPorta
LightNews LightNews
johndellaporta.bsky.social
Guys I was on TV and I’m never gonna stop thinking that was the coolest thing ever and god do I wanna do it again soon

youtu.be/vvMYbRbZXGE?...
November 8, 2024 at 6:51 AM
underbellypress.bsky.social
SF
Alan Brickman☆ @wordsbyalice.bsky.social ☆Elia Rathore☆ Elinor Drew☆ @therelphian.bsky.social ☆ @jpcerthum.bsky.social ☆ @johannah.bsky.social ☆Jorden Makelle☆ @judepickledplum.bsky.social ☆Lisa DellaPorta☆ @miketaylor9.bsky.social ☆ @aldbera.bsky.social ☆Simon Collinson☆ @zaryfekete.bsky.social
June 20, 2025 at 3:39 PM
underbellypress.bsky.social
SF
Alan Brickman☆ @wordsbyalice.bsky.social ☆Elia Rathore☆ Elinor Drew☆ @therelphian.bsky.social ☆ @jpcerthum.bsky.social ☆ @johannah.bsky.social ☆Jorden Makelle☆ @judepickledplum.bsky.social ☆Lisa DellaPorta☆
@miketaylor9.bsky.social ☆ @aldbera.bsky.social ☆Simon Collinson☆ @zaryfekete.bsky.social
July 3, 2025 at 11:38 PM
fxbriol.bsky.social
Our event on 'Computational Statistics and Machine Learning in the sciences' is taking place tomorrow at the London Mathematical Society.

Our stellar line-up includes Harita Dellaporta, Jason McEwen, Ziheng Yang, Ziheng Yang, Marta Betcke, and Sam Livingstone.

Details: www.ucl.ac.uk/data-science/
December 4, 2024 at 11:56 AM
lisadellaporta.bsky.social
Very happy to have a little essay out in Corporeal today on dietary restrictions and disability in the Trump tariff era: www.corporeallitmag.com/volume-xix/l...
Lisa DellaPorta — Corporeal
The threat of tariffs and their likelihood to disrupt the supply chain for my sustenance is something that keeps me up at night.
www.corporeallitmag.com
June 24, 2025 at 2:53 PM
arxiv-stat-ml.bsky.social
Charita Dellaporta, Patrick O'Hara, Theodoros Damoulas
Decision Making under Model Misspecification: DRO with Robust Bayesian Ambiguity Sets
https://arxiv.org/abs/2505.03585
May 7, 2025 at 4:11 AM
fxbriol.bsky.social
We also have excellent line-up of invited speakers which includes @pierrealquier.bsky.social, @eweinstein.bsky.social, Jeremias Knoblauch, David Frazier, Harita Dellaporta, Antonietta Mira, Jeremie Houssineau, Sonia Petrone, Edwin Fong and Aretha Teckentrup.
April 2, 2025 at 3:04 PM
ouisequitur.bsky.social
what dellaporta said.
johndellaporta.bsky.social John Dellaporta @johndellaporta.bsky.social · Nov 13
It’s because interesting people make their interests seem interesting. It’s marvelous storytelling and teaching!
November 13, 2024 at 8:53 PM
statml-bot.bsky.social
Ayush Bharti, Charita Dellaporta, Yuga Hikida, Fran\c{c}ois-Xavier Briol: Amortised and provably-robust simulation-based inference https://arxiv.org/abs/2602.11325 https://arxiv.org/pdf/2602.11325 https://arxiv.org/html/2602.11325
February 13, 2026 at 6:53 AM
mrbullbull.bsky.social
"The man sent thinly veiled declarations of love & detailed accounts of his struggles with unmedicated depression with his hopes for improvement pinned squarely on my mother returning his affections. When I asked, my mother simply shrugged." - Lisa Dellaporta mrbullbull.com/newbull/flas...
October 18, 2024 at 10:47 AM
qberthet.bsky.social
2) "OPTIMAL: (O)ptimisation and (P)os(T)-Bayesian (I)nference in (MA)chine (L)earning"

optimal-workshop26.github.io

organized by K. Daudel, J. Knoblauch, S. Filippi, V. Fortuin, T. Möllenhoff, J. Odgers, C. Tsay, C. Dellaporta, M. Altamirano, Y. McLatchie
optimal - OPTIMAL: Optimisation and Post-Bayesian Inference in Machine Learning
optimal-workshop26.github.io
February 18, 2026 at 1:37 PM
underbellypress.bsky.social
This week’s Sunday Snippet gives you a bite of Forbidden Fruit by @lisadellaporta.bsky.social
With evocative and stunning detail, Lisa deftly builds dread beneath the thrill, capturing how desire and secrecy unravel into danger and discovery.

Read here: underbellypress.wixsite.com/home/copy-of...
Sunday Snippets But he’s running ahead of me now, disappearing between the rows, out of sight, soundtracked to the heavy rasp of canine panting. I am alone as they circle, barefooted as I was born, sticky with my shame. Forbidden Fruit Lisa DellaPorta Text is on a black background. Image of a glowing moon in the bottom right corner.
October 19, 2025 at 5:06 PM
playcritically.bsky.social
Suddenly felt like that time my friend @johndellaporta.bsky.social was on a Star War should be immortalized on biskey.
An arrow points to actor John Dellaporta as a background character in a scene from Disney's Star Wars: Obi-Wan Kenobi.
October 9, 2023 at 5:53 PM
optb0t.bsky.social
🔄 Updated Arxiv Paper

Title: Decision Making under the Exponential Family: Distributionally Robust Optimisation with Bayesian Ambiguity Sets
Authors: Charita Dellaporta, Patrick O'Hara, Theodoros Damoulas

Read more: https://arxiv.org/abs/2411.16829
June 13, 2025 at 8:15 AM
warwickstats.bsky.social
Two papers by Prof. Theo Damoulas’ group and led by Dr. Dellaporta (Stats), Dr. O’Hara (CS) and Terje Mildner (4th year CS-DM UG) were accepted as spotlights (2.6% of submitted papers) at ICML 2025...
July 1, 2025 at 11:00 AM
goossen.bsky.social
Wat een prachtige en interessante documentaire over de geschiedenis van het #Vaticaan, vanmiddag op #VRTCanvas.
Building the Vatican: secrets behind the holy city: www.vrt.be/vrtmax/a-z/b...

#Rome #Bramante #Pantheon #MichelAngelo #SintPieter #SixtijnseKapel #DellaPorta
December 14, 2024 at 8:23 PM
www.threads.com/@johndellapo...
John Dellaporta (@johndellaporta) on Threads
Now that I’m seeing the photos, I’m starting to “get” the Vanity Fair piece, and it may turn out to be one of the ballsiest things a mainstream media outlet has done in the decade since Trump invaded ...
www.threads.com
December 17, 2025 at 1:19 PM
lisadellaporta.bsky.social
Do you -also- listen to weird new age pseudoscience on YouTube ? Then maybe this one's for you. I have a new poem out today in Stink Eye Magazine: stinkeyemagazine.com/lisa-dellapo...
Lisa DellaPorta
On the baffling fallacy of the Reiki crystal quantum healing woman (ASMR)  Undergrad, masters, then doctorate:a herculean effort to prove my dedication.In the day, I am a nonbeliever, adevotee…
stinkeyemagazine.com
December 20, 2025 at 5:37 PM
johndellaporta.bsky.social
Look I knew if I got angry at Elon and join them all I’d eventually be in a winning club…
A virtual certificate with text "Celebrating 10M users on Bluesky, #187,639, John Dellaporta ‪@johndellaporta.bsky.social‬, joined on Jul 1, 2023"
September 20, 2024 at 6:17 AM
davidaugust.bsky.social
The CEOs and their AMPTP need to act like adults and come back to the conversations, today.

via @johndellaporta.bsky.social
Screenshot of a tweet by John Dellaporta SAG•AFTRA STRIKE! @JohnDellaporta: What an asinine statement. "Oh well, we tried! No more movies or TV, sorry!" The era of "let's stop making the thing we make" is coming to a crashing end with CEOs immolating their own businesses. #SAGAFTRAstrong [screenshot of an article:] The studios presented their late at offer on Wednesday. In the statement, the AMPTP said, "After meaningful conversations, it is clear that the gap between the AMPTP and SAG-AFTRA is too great, and conversations are no longer moving us in a productive direction." 10:34 AM • 10/12/23 from Earth
October 12, 2023 at 5:30 PM
paperposterbot.bsky.social
arXiv📈🤖
Amortised and provably-robust simulation-based inference
By Bharti, Dellaporta, Hikida et al
Complex simulator-based models are now routinely used to perform inference across the sciences and engineering, but existing inference methods are often unable to account for outliers and other extreme values in data which occur due to faulty measurement instruments or human error. In this paper, we introduce a novel approach to simulation-based inference grounded in generalised Bayesian inference and a neural approximation of a weighted score-matching loss. This leads to a method that is both amortised and provably robust to outliers, a combination not achieved by existing approaches. Furthermore, through a carefully chosen conditional density model, we demonstrate that inference can be further simplified and performed without the need for Markov chain Monte Carlo sampling, thereby offering significant computational advantages, with complexity that is only a small fraction of that of current state-of-the-art approaches.
March 10, 2026 at 10:08 PM
paperposterbot.bsky.social
arXiv📈🤖
Amortised and provably-robust simulation-based inference
By Bharti, Dellaporta, Hikida et al
Complex simulator-based models are now routinely used to perform inference across the sciences and engineering, but existing inference methods are often unable to account for outliers and other extreme values in data which occur due to faulty measurement instruments or human error. In this paper, we introduce a novel approach to simulation-based inference grounded in generalised Bayesian inference and a neural approximation of a weighted score-matching loss. This leads to a method that is both amortised and provably robust to outliers, a combination not achieved by existing approaches. Furthermore, through a carefully chosen conditional density model, we demonstrate that inference can be further simplified and performed without the need for Markov chain Monte Carlo sampling, thereby offering significant computational advantages, with complexity that is only a small fraction of that of current state-of-the-art approaches.
February 13, 2026 at 7:48 PM
wasnu.bsky.social
Hatte das hier gelesen und es erklärt es zumindest ein wenig:

Beide Seiten werden mit anderen Maßstäben bemessen, die Erwartungshaltung ist eine andere
John Dellaporta @johndellaporta.bsky.... A few years ago, Jon Lovett floated a theory that media treats Democrats like protagonists - to be challenged, accounted, and forced to be behave in growth-oriented ways - while the GOP are treated like antagonists - immutable, expected to disrupt, thematic obstacles. Thinking about that a lot. darkwebmallcop.bsky.social @... • 4d I don't recall the NYT calling for Trump to step down after being convicted of 34 counts of fraud and being called by a judge at his civil trial a rapist in the common person sense Jun 29, 2024 at 06:07
July 20, 2024 at 8:04 AM
playcritically.bsky.social
Is "pilot season" even still a thing anymore? John Dellaporta, help me out here.
August 14, 2023 at 8:30 PM
paperposterbot.bsky.social
arXiv📈🤖
A computationally-tractable measure of global sensitivity for sampling-based Bayesian inference
By Odnoblyudova, Dellaporta, Briol
Bayesian inference can often be sensitive to the choice of hyperparameters of the prior or likelihood, yet defining and quantifying this sensitivity in a principled and computationally feasible way remains challenging in practice. Unfortunately, existing sensitivity methods are rarely applicable in modern Bayesian workflows due to their high computational cost and poor performance in moderate to high dimensions. To address these limitations, we introduce a new approach to global sensitivity analysis based on the Fisher divergence. Our method only requires a set of samples from a reference posterior and the ability to evaluate score functions, making it broadly computationally tractable. Under mild regularity conditions, it controls changes in the whole posterior, and provides a bound on the impact of perturbations on the first two moments. We demonstrate these strengths on challenging Bayesian inference problems which are practically out of reach of existing approaches, including generalised Bayesian inference for unnormalised models, inference in Bayesian models of time series, and neural simulation-based inference.
May 28, 2026 at 4:50 AM