DR MAURIZIO FILIPPONE
Photo
Associate Professor with the Statistics Program at KAUST

Address:
4700 King Abdullah University Of Science And Technology
Thuwal 23955-6900,
Kingdom of Saudi Arabia

Office: 1-4112

Phone: +966 12 808 7216

Email Address: maurizio.filippone [at] kaust.edu.sa



**** A message to perspective Post-Docs and PhD candidates ****

I'm always looking for talented students and Post-Docs who are passionate about Computational Statistics and Probabilistic Machine Learning. If you are interested in joining my group at KAUST, please get in touch!



NEWS

22-01-25  The paper "Zero-shot Model-based Reinforcement Learning using Large Language Models" has been accepted at ICLR 2025! (link)

22-01-25  The paper "Robust Classification by Coupling Data Mollification with Label Smoothing" has been accepted at AISTATS 2025! (link)

22-01-25  The paper "Unconditionally Calibrated Priors for Beta Mixture Density Networks" has been accepted at AISTATS 2025!

10-06-24  Invited talk at the "Recent Advances on High Dimensional Models" session of the ICSDS conference in Nice: "Improving Optimization of Likelihood-based Generative Models with One Line of Code" (link)

01-12-24  Applied Mathematics School at KAUST happening this week (link)

17-11-24  Workshop of Statistics at KAUST happening this week (link)

10-11-24  Participating in the Dagstuhl seminar Rethinking the Role of Bayesianism in the Age of Modern AI organized by V. Fortuin, Z. Ghahramani, M. E. Khan, M. van der Wilk (link)

10-08-24  The paper "Improved Random Features for Dot Product Kernels" has been accepted for publication in JMLR! (link)

08-08-24  Invited talk at the session on Advances in Inference and Theory for Bayesian Neural Networks at JSM in Portland, OR "Functional Priors for Bayesian Deep Learning" (link)

10-06-24  Invited talk at the Approximate Inference in Theory and Practice workshop in Paris: "Improving Optimization of Likelihood-based Generative Models with One Line of Code" (link)

02-05-24  The position paper entitled "Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI" has been accepted at ICML 2024! (link)

11-04-24  The paper "Spatial Bayesian neural networks" has been accepted in the Spatial Statistics journal! (link)

18-02-24  I moved to KAUST as an Associate Professor of Statistics!

21-09-23  The paper "One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models" has been accepted at NeurIPS 2023! (link)

21-09-23  The paper "Continuous-Time Functional Diffusion Processes" has been accepted at NeurIPS 2023! (link)

20-09-23  Delighted to be an invited speaker at the GenU workshop in Copenhagen presenting "Bayesian Autoencoders" (link)

25-07-23  Poster presentation at ICML of our paper "Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes" (link)

23-07-23  Delighted to be an invited speaker at the AABI workshop at ICML, presenting "Bayesian Autoencoders" (link)

30-05-23  Check out our new paper "One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models" (link)

...