Please have a look at open positions in our group. See here for more details and join our team.

June 12, 2024

We are holding the 2nd Bayes-duality workshop 2024 (June 12-21), focusing on the design of AI that learns adaptively, robustly, and continually, like humans. Part 1 of the workshop is open to the public (through live streaming) and will feature 26 talks, 7hrs of tutorials, and panel discussions by world-leading researchers working on related topics. Register here

June 07, 2024

Our paper Variational Learning is Effective for Large Neural Networks is now published at ICML 2024. Also check out our blog post for additional remarks and explanations and find the code here.

June 05, 2024

Hugo Monzon and Thomas Möllenhoff are giving poster presentations at the RIKEN-LAMDA workshop in Nanjing, China.

June 04, 2024

Thomas Möllenhoff gave a guest talk at SambaNova Systems on model merging.

May 23, 2024

Emtiyaz Khan gave a talk at the HKBU-COMP and RIKEN-AIP Joint Workshop.

May 21, 2024

Thomas Möllenhoff gave a talk at the joint symposium of RIKEN AIP and the Italian Institute of Technology.

May 17, 2024

Emtiyaz Khan gave a tutorial at the Tunisian AI Society. Slides

April 25, 2024

Emtiyaz Khan gave an invited talk at IIT, Hyderabad, India. Slides

April 19, 2024

Emtiyaz Khan gave a talk at RIKEN CBS.

April 16, 2024

Emtiyaz Khan gave a talk at Integreat Tuesday seminar.

March 19, 2024

Emtiyaz Khan is an invited talk at the Deep Learning Workshop 2024 [Slides]

March 14, 2024

Emtiyaz Khan gave an invited talk at the Workshop on Optimal Transport in Berlin. Thomas Möllenhoff gave an invited talk at Weierstraß-Instutit in Berlin and visited Jia-Jie Zhu’s group.

January 17, 2024

We have two papers accepted to ICLR 2024:

January 04, 2024

Geoffrey Wolfer gave an invited talk at IMS-APRM 2024.

October 20, 2023

New preprint avilable: Model Merging by Uncertainty-Based Gradient Matching.

September 23, 2023

Emtiyaz Khan is co-organizing a Dagstuhl Seminar On the Role of Bayesianism in the Age of Modern AI. It will be held from Nov. 10 - Nov. 15, 2024.

September 22, 2023

One paper (The Memory Perturbation Equation: Understanding Model’s Sensitivity to Data) accepted at NeurIPS 2023.

September 21, 2023

The Bayesian Learning Rule is accepted for publication at JMLR.

September 02, 2023

Our paper on Bridging the Gap Between Target Networks and Functional Regularization is accepted at TMLR.

September 01, 2023

Emtiyaz Khan will serve as a program chair for AISTATS 2025.

August 18, 2023

So Takao, Molei Tao and Rajesh Ranganath are visiting our group. See our reading-group page for more information about their talks.

July 29, 2023

Thomas Moellenhoff and Emtiyaz Khan are organizing the Duality Principles for Modern ML Workshop at ICML 2023 in Hawaii.

July 21, 2023

From August 2 to August 9, Emtiyaz Khan, Gian Maria Marconi and Lu Xu will be giving invited talks at the Machine Learning Research School (MLRS), Bangkok, Thailand.

July 11, 2023

Emtiyaz Khan will present VB Made Easy at AABI 2023.

June 15, 2023

We are organizing the first Bayes-duality workshop in Japan.

June 07, 2023

Ang Ming Liang’s (NUS) undergraduate thesis (done at RIKEN as a remote collaborator) was awarded “Lijen Industrial Development medal” for best academic projects in the discipline. His thesis was on the Knowledge Adaptation Prior paper by Khan and Swaroop (NeurIPS 2021).

May 23, 2023

G. Wolfer was awarded a KAKENHI Grant-in-Aid for Early-Career Scientists (Apr. 2023- Mar. 2026, USD ~32,000).

April 27, 2023

Emtiyaz Khan is giving an invited talk at the One World ABC Seminar.

April 24, 2023

Two papers accepted at ICML 2023 on “Memory-based Dual GPs” and Momentum-based Riemannian Optimization respectively.

April 14, 2023

Our Dagstuhl Seminar on AI for Social good (part III) is accepted (to be held Feb 19-23, 2024); see the first meeting details here

April 06, 2023

Emtiyaz Khan and Thomas Möllenhoff are co-organizing (with Mathieu Blondel and Zelda Mariet) the ICML 2023 Workshop on Duality Principles in Modern Machine Learning! See the workshop webpage for more details and the call for papers.

January 30, 2023

Our work “SAM as an Optimal Relaxation of Bayes” (T. Moellenhoff and M. E. Khan) is accepted at ICLR 2023 (notable top 5%). We have another paper “The Lie-Group Bayesian Learning Rule” (E. M. Kiral, T. Moellenhoff, M.E. Khan) accepted at AISTATS 2023.

January 20, 2023

Happy Buzaaba is co-organizing the ICLR2023 workshop on AfricaNLP to be held on 5th May in Kigali, Rwanda.

December 12, 2022

We organized the “Continual Lifelong Learning Workshop” at ACML2022 in Hyderabad, India.

December 08, 2022

Invited Prof. Michael Choi (National University of Singapore and Yale-NUS College) for a seminar talk. Title “From reversiblizations of non-reversible Markov chains to landscape modification”.

December 03, 2022

Emtiyaz Khan gave an invited talk at NeurIPS 2022 Workshop on Broadening Research Collaborations in Machine Learning [Slides].

November 24, 2022

Emtiyaz Khan gave an invited talk at University of Bath in Prof. Olga Isupova’s group [Slides].

November 09, 2022

Today, we hosted Prof. Yarin Gal for a seminar on “Uncertainty in Deep Learning: Lessons Learned from Medical Imaging”.

November 01, 2022

The ABI team is organizing a seminar on Tuesday, November 1st.

October 25, 2022

Forthcoming talks by Geoffrey Wolfer:

  • [16 Nov, 2022] [ CCSP Seminar ] Talk: "Geometric Aspects of Markov Models"
  • [22 Nov, 2022] [ IBIS'22 ] Poster: "Variance-Aware Estimation of Kernel Mean Embedding"
  • [1 Dec, 2022] [ SITA'22 ] Talk: "Markovian Embeddings of Markov Chains"

October 24, 2022

Pierre will visit Toulouse School of Economics as an invited researcher in November. He will give a series of 5 lectures at on PAC-Bayes and Mutual Information bounds, on Nov. 8, 15, 21, 22 and 28. The lectures are intended for PhD students but will be also opened for master students. They will be essentially based on User-friendly introduction to PAC-Bayes bounds. He will also give the following talks:

September 02, 2022

Forthcoming talks by Geoffrey Wolfer:

  • [19 Sep, 2022] [ IG4DS ] Talk: "Information Geometry of Reversible Markov Chains" [ Slides ] [ Video ]
  • [20 Sep, 2022] [ IG4DS ] Talk: "Geometric Aspects of Data-Processing of Markov Chains" [ Slides ] [ Video ]
  • [26 Sep, 2022] [ BIID'10 ] Talk: "Geometric Aspects of Data-Processing of Markov Chains"

August 24, 2022

Forthcoming talk by Pierre:

May 26, 2022

[ ENTROPY ] special issue on Approximate Bayesian Inference (edited by Pierre) is now available as a book and as a pdf file that can be downloaded for free on the editor website: [ Book page ]

May 01, 2022

Recent talks by Pierre:

  • [20 Jan, 2022] StatML CDT seminar (Imperial & Oxford): "Matrix factorization for time series analysis" [ Slides ]
  • [02 Feb, 2022] Invited talk at [ AABI2022 ] "What to expect from PAC-Bayes bounds" [ Slides ] [ Video ]
  • [03 Mar, 2022] RIKEN AIP High-dimensional modelling team seminar: "Deviation inequalities for Markov chains" [ Slides ] [ Video ]
  • [19 Apr, 2022] [ DELTA ] Seminar: "PAC-Bayes bounds and contraction of the posterior"
  • [21 Apr, 2022] [ International Bayes Club ] Seminar: "PAC-Bayes bounds and contraction of the posterior"
  • [28 Apr, 2022] [ One World ABC ] Seminar: "Concentration and robustness of discrepancy-based ABC" [ Slides ] [ Video ]

Forthcoming talks:

March 30, 2022

Emtiyaz Khan gave the following talks in March and Feb, 2022

December 08, 2021

Emtiyaz Khan, Dharmesh Tailor and Siddharth Swaroop will be giving an invited talk on Adaptive and Robust Learning with Bayes at the NeurIPS 2021 Bayesian deep learning workshop on Dec. 14th 11:10 - 11:30 GMT.

December 06, 2021

We won both tracks of the NeurIPS competition on Approximate Inference in Bayesian Deep Learning! Please join our talks at the NeurIPS 2021 competition track (Dec. 9th, 6pm GMT) and at the BDL workshop (Dec. 14th, 4:40pm GMT) to learn about our solution.

October 22, 2021

On arXiv today: User-friendly introduction to PAC-Bayes bounds by P. Alquier

October 01, 2021

Our Bayes-duality project is launched with a funding of $2.76 million by JST-ANR’s CREST proposal

September 30, 2021

Invited talk by Pierre Alquier at AmLab (Amsterdam) on [MMD based estimation]

September 29, 2021

Two papers accepted at NeurIPS 2021:

September 28, 2021

Paper by Dimitri Meunier & Pierre Alquier accepted+published in Entropy: [Meta-strategy for Learning Tuning Parameters with Guarantees]

September 21, 2021

Invited talk by Emtiyaz Khan at Tübingen AI Center (Philipp Hennig’s group).

September 17, 2021

Invited talk by Emtiyaz Khan at Secondmind.

September 16, 2021

Invited talk by Emtiyaz Khan at Durham CDT Data Science Workshop.

September 13, 2021

Invited talk by Pierre Alquier at Ecology and Dependance 2021 (EcoDep) on [ Risk Bound for High Dimensional Time Series Completion ]

August 15, 2021

Invited talk by Emtiyaz Khan at KDD workshop 2021 Model Mining [ Slides ]

July 23, 2021

Invited talk by Emtiyaz Khan at Theory and Foundation of Continual Learning [ Slides ] [ SlidesLive Video ]

July 09, 2021

A new paper on Bayesian Learning Rule by M.E. Khan and H. Rue.

May 13, 2021

One paper accepted at UAI2021: Subset-of-Data Variational Inference for Deep Gaussian-Process Regression by A. Jain, P.K. Srijith, M.E. Khan.

May 10, 2021

Three papers were accepted at ICML2021:

March 10, 2021

16th AIP Open Seminar: talks by Approximate Bayesian Inference Team. Talks by

January 28, 2021

Two papers were accepted at AISTATS2021:

November 11, 2020

“Approximate Bayesian Inference”, the editorial of a forthcoming special issue in Entropy, written by P. Alquier, is now published: paper. You can submit a paper until the end of Feb. 2021. Special Issue on Approximate Bayesian Inference

November 05, 2020

The videos of two recent talks by Pierre Alquier are now online:

November 02, 2020

A series of seminars on “Bayesian principles for learning machines” held by Emtiyaz Khan will take place at the following dates and locations.

October 06, 2020

Pierre Alquier joined the editorial board of JMLR.

September 26, 2020

Our paper on continual learning by functional regularization on the memorable past is accepted as an oral presentation at NeurIPS 2020.

September 07, 2020

New preprint by Pierre Alquier on online learning with unbounded loss functions.

August 17, 2020

We have two tutorials at SMILES 2020! See Emtiyaz Khan’s tutorial on DL with Bayes (slides, video) and Pierre Alquier on Sequential Prediction Problems (video).

July 20, 2020

New tutorial by Emtiyaz Khan on DL with Bayes at SPCOM 2020. [slides] [video]

May 12, 2020

Emtiyaz Khan gave a talk on DNN2GP.

April 01, 2020

Emtiyaz Khan received a Kakenhi Grant (Series B) on “life-long learning” (approx. USD 158K).