George Deligiannidis (@georgedeligian9) 's Twitter Profile
George Deligiannidis

@georgedeligian9

Professor of Statistics @ Oxford

ID: 1004801822522036226

linkhttp://www.stats.ox.ac.uk/~deligian calendar_today07-06-2018 19:06:37

162 Tweet

550 Followers

416 Following

Valeriy M., PhD, MBA, CQF (@predict_addict) 's Twitter Profile Photo

Conformal prediction provides valid prediction regions for any machine learning model, any data distribution and and any dataset size. But what determines the size of prediction sets and can this itself size be predicted? I turns out that the answer is yes 🔥🔥🔥🔥 as shown in

Conformal prediction provides valid prediction regions for any machine learning model, any data distribution and and any dataset size.

But what determines the size of prediction sets and can this itself size be predicted? I turns out that the answer is yes 🔥🔥🔥🔥 as shown in
Oxford Statistics (@oxfordstats) 's Twitter Profile Photo

We are recruiting a Postdoctoral Research Assistant working with Prof Patrick Rebeschini. Grade 7: £35,308-£43,155 per annum, fixed term for 24 months. stats.ox.ac.uk/jobs 📸Vivacious Mel Photography

We are recruiting a Postdoctoral Research Assistant working with Prof Patrick Rebeschini. Grade 7: £35,308-£43,155 per annum, fixed term for 24 months. stats.ox.ac.uk/jobs 📸Vivacious Mel Photography
Oxford Statistics (@oxfordstats) 's Twitter Profile Photo

Congratulations to Dr Neil Laws, who has won a 2023 MPLSOxford Teaching Award for his pivotal role in numerous teaching innovations in recent years. A very well deserved award. stats.ox.ac.uk/news/neil-laws…

Congratulations to Dr Neil Laws, who has won a 2023 <a href="/mplsoxford/">MPLSOxford</a>  Teaching Award for his pivotal role in numerous teaching innovations in recent years.  A very well deserved award. stats.ox.ac.uk/news/neil-laws…
Dalalyan Arnak (@arnakdalalyan) 's Twitter Profile Photo

The Statistics and Learning Theory Summer School 2023 started yesterday. Amazing mini-courses taught by Evgenii Chzhen, Maxim Panov, Patrick Rebeschini and Martin Takac. Gorgeous place and highly motivated participants.

The Statistics and Learning Theory Summer School 2023 started yesterday. Amazing mini-courses taught by Evgenii Chzhen, <a href="/maxim_panov/">Maxim Panov</a>, Patrick  Rebeschini and Martin Takac. Gorgeous place and highly motivated participants.
Joe Benton (@joejbenton) 's Twitter Profile Photo

Excited that our work ‘From Denoising Diffusions to Denoising Markov Models’ has been accepted to JRSS-B for discussion! In it, we generalise diffusion models to arbitrary spaces. arxiv.org/abs/2211.03595 w/ Yuyang Shi Valentin De Bortoli George Deligiannidis Arnaud Doucet 🧵1/n

Excited that our work ‘From Denoising Diffusions to Denoising Markov Models’ has been accepted to JRSS-B for discussion!

In it, we generalise diffusion models to arbitrary spaces.

arxiv.org/abs/2211.03595

w/ <a href="/YuyangShi0/">Yuyang Shi</a> <a href="/ValentinDeBort1/">Valentin De Bortoli</a> <a href="/GeorgeDeligian9/">George Deligiannidis</a> <a href="/ArnaudDoucet1/">Arnaud Doucet</a> 🧵1/n
Dr James Pickles (@readitpickles) 's Twitter Profile Photo

This is my meal for tonight because all I can afford is donated potatoes and a tin of beans since University of Brighton stole 100% of my wages for not marking 3 dissertations. This is how lecturers are treated here, which UCU Brighton UCU are trying to change. Help Jack Monroe

This is my meal for tonight because all I can afford is donated potatoes and a tin of beans since <a href="/uniofbrighton/">University of Brighton</a> stole 100% of my wages for not marking 3 dissertations. This is how lecturers are treated here, which <a href="/ucu/">UCU</a> <a href="/BrightonUCU/">Brighton UCU</a> are trying to change. Help <a href="/BootstrapCook/">Jack Monroe</a>
Joe Benton (@joejbenton) 's Twitter Profile Photo

📰Our work on error bounds for flow matching methods has just been accepted to TMLR! We derive the first error bounds that apply in the case of fully deterministic sampling and data distributions without full support. w/ Arnaud Doucet George Deligiannidis arxiv.org/abs/2305.16860

James Thornton (@jamestthorn) 's Twitter Profile Photo

Is optimal transport always optimal? By learning ground costs (ICNNs+flows) one can structure OT maps to use prior information Brilliant PhD student, Samuel Howard, will be presenting Cost-Parameterized Monge Maps at the Differentiable AE workshop differentiable.xyz/papers-2024/pa…

Is optimal transport always optimal? 

By learning ground costs (ICNNs+flows) one can structure OT maps to use prior information

Brilliant PhD student, Samuel Howard, will be presenting  Cost-Parameterized Monge Maps at the  Differentiable AE workshop

differentiable.xyz/papers-2024/pa…
Chris J. Maddison (@cjmaddison) 's Twitter Profile Photo

What if the next medical breakthrough is hidden in plain text? Causal estimates drives progress but data is limited & RCTs slow. Introducing NATURAL: a pipeline for causal estimation from text data in hours, not years. Paper: tinyurl.com/ppr29 Site: tinyurl.com/web98

What if the next medical breakthrough is hidden in plain text? Causal estimates drives progress but data is limited &amp; RCTs slow. Introducing NATURAL: a pipeline for causal estimation from text data in hours, not years.
Paper: tinyurl.com/ppr29
Site: tinyurl.com/web98
Oxford Statistics (@oxfordstats) 's Twitter Profile Photo

Congratulations to George Deligiannidis & Julien Berestycki on the award of Full Professor title! 🎉 They have been promoted through the University of Oxford Recognition of Distinction 2024 round. The title acknowledges their achievements in research, teaching & good citizenship.

Congratulations to <a href="/GeorgeDeligian9/">George Deligiannidis</a> &amp; <a href="/JBerestycki/">Julien Berestycki</a> on the award of Full Professor title! 🎉
They have been promoted through the <a href="/UniofOxford/">University of Oxford</a> Recognition of Distinction 2024 round. The title acknowledges their achievements in research, teaching &amp; good citizenship.
Iskander Azangulov (@iazangulov) 's Twitter Profile Photo

Convergence of Diffusion Models Under the Manifold Hypothesis in High-Dimensions arxiv.org/abs/2409.18804… Jointly with George Deligiannidis and Judith Rousseau, we show that diffusion models achieve rates independent of the ambient dimension for score learning and sampling! (1/4)

Oxford Statistics (@oxfordstats) 's Twitter Profile Photo

We would like to invite new staff and students of the Department of Statistics to our department welcome drinks! 🍸 📆Date: 15.10.2024 ⌚️Time: 4.30pm 📍Location: Ground Floor Social Area We look forward to welcoming our new members to the department 🥳 #MT24

We would like to invite new staff and students of the Department of Statistics to our department welcome drinks! 🍸 

📆Date: 15.10.2024
⌚️Time: 4.30pm
📍Location: Ground Floor Social Area

We look forward to welcoming our new members to the department 🥳

#MT24
Iskander Azangulov (@iazangulov) 's Twitter Profile Photo

With Peter Potaptchik and George Deligiannidis we show the first realistic bound on the iteration complexity of diffusion models! Our work explains why sampling from ImageNet needs only ~100 (intrinsic dim) steps instead of ~150k (extrinsic dim). arxiv.org/abs/2410.09046

With <a href="/PPotaptchik/">Peter Potaptchik</a> and <a href="/GeorgeDeligian9/">George Deligiannidis</a> we show the first realistic bound on the iteration complexity of diffusion models!

Our work explains why sampling from ImageNet needs only ~100 (intrinsic dim) steps instead of ~150k (extrinsic dim).

arxiv.org/abs/2410.09046
Tyler Farghly (@tylerfarghly) 's Twitter Profile Photo

Attending ALT 2025 in Milan Come say hi! Presenting “Generalisation under gradient descent via deterministic PAC-Bayes” on Thu w/ Eugenio Clerico George Deligiannidis Benjamin Guedj Arnaud Doucet proceedings.mlr.press/v272/clerico25…