Emtiyaz Khan

Research

Humans, animals, and other living beings have a natural ability to autonomously learn throughout their lives and quickly adapt to their surroundings, but computers lack such abilities. My goal is to bridge such gaps between the learning of living-beings and computers.

My current focus is on AI that can autonomously learn to perceive, act, and reason throughout their lives.

I work on problems in several areas of machine learning, such as approximate inference, deep learning, reinforcement learning, active learning, online learning, and reasoning in computer vision. In my recent works, I have worked on ideas from a wide range of fields, such as, optimization, Bayesian statistics, information geometry, signal processing, and control systems.

For details of my research activites, see the following pages,

• Approximate Bayesian Inference team at RIKEN-AIP
• The Bayes-Duality Project (funded by CREST)
• Summary of research for the year [2022] [2021] [2019] [2018] [2017]

We are also thankful to receive the following external funding (funding amount is approximate),

• (2021-2026, USD 2.23 Million) JST-CREST and French-ANR's grant, The Bayes-Duality Project
• (2020-2023, USD 167,000) KAKENHI Grant-in-Aid for scientific Research (B), Life-Long Deep Learning using Bayesian Principles
• (2020-2023, USD 11,000) KAKENHI Grant-in-Aid for Chellenging Research (Exloratory), Linear algebra for continuous learning of large neural networks, PI: Rio Yokota, Total Budget: JPY 19,710,000
• (2019-2022, USD 237,000) External funding through companies for several Bayes related projects

Research Highlights

• SAM as Bayes
• The Bayesian Learning Rule
• Knowledge-Adaptation Priors
• Talk at AIP open seminar [ Video ] [ Slides ]
• Continual Deep Learning by Functional Regularisation of Memorable Past
• My NeurIPS 2019 Tutorial on "Deep learning with Bayesian principles" is the third most popular talk at NeurIPS 2019! See Slides, or watch it on SlidesLive or YouTube.
• Practical Deep Learning with Bayesian Principles
• Approximate Inference Turns Deep Networks into Gaussian Processes
• Bayesian Deep Learning using Weight-Perturbation in Adam (code here)
• Conjugate-Computation Variational Inference (CVI).

Service

• Program Chair for AISTATS 2025
• Program Chair for ICLR 2024
• Senior Area-Chair for NeurIPS 2023 (handling around 140 papers)
• ISBA 2024 Scientific Committee
• Reviewer for ICML 2023 Workshop Proposals (reviewing 8 proposals)
• Senior Area-Chair for AISTATS 2023 (handling 65 papers)
• Senior Area-Chair for ICLR 2023 (handling about 130 papers)
• Advisory committee member for NeurIPS 2023 workshop on "GPs, spatiotemporal modeling and Decision making"
• Senior Area-Chair for NeurIPS 2022 (handling about 100 papers)
• Program Chair for ACML 2022 (handling 265 papers)
• Senior Area-Chair for ICLR 2022 (handing around 150 papers)
• Workshop Co-Chair for ACML 2021
• Senior Area-Chair for NeurIPS 2021 (handing around 135 papers)
• Meetups Chair for NeurIPS 2021
• Mentorship Session Chair for AISTATS 2021
• Co-founder for MeMentor, a mentorship portal for ML researchers
• Area chair for AIStats 2021, ICML 2021
• Reviewer for NeurIPS workshop 2020
• Equity, Diversity and Inclusion (EDI) chair for ICLR 2021
• Meetups Chair for NeurIPS 2020
• Workshop Chair for ICML 2020
• Senior AC for IJCAI-PRECAI 2019
• Tutorials Chair for ACML 2019
• I have reviewed or been an Area Chair or Action editor for (approximate numbers)
  • 6 papers to review in 2022. Handling +130 papers as SAC in NeurIPS 2022, +265 as Program chair at ACML 2022, +130 at ICLR 2022, +65 at AISTATS 2023, +8 at NeurIPS workshop, and +10 or so in JMLR.
  • 32 papers in 2021 (+135 papers as Senior AC in NeurIPS 2021 and 150 at ICLR 2022)
  • 34 papers in 2020,
  • 62 papers in 2019,
  • 70 papers in 2018,
  • 54 papers in 2017.