We aim to develop sustainable and transparent Artificial Intelligent (AI) systems. The goal is twofold: one, to break free from heavy dependence on extremely large data sets, computations, and energy sources, and two, to build systems with transparent functionalities. We plan to achieve these goals by developing AI systems that can learn via quick and continual adaptation, similarly to humans and animals. Our research relies on a mix of techniques from a wide variety of fields, such as deep learning, statistics, and optimization, covering both theoretical and practical tools.
For more information, see our current publications and the following pages:
We are also thankful to receive the following external funding (funding amount is approximate),
This blog provides a medium for our researchers to present their recent research findings, insights and updates. The posts in the blog are written with a general audience in mind and aim to provide an accessible introduction to our research.
Bayesian methods are considered impractical at large scale, and even when we are able to make them work for large deep networks (say using approximations), we don’t expect them to match the performance of optimizers... Continue
What makes a good meta-review? It clearly describes the whole review process and gives clear reasons behind the decisions. Below are a few tips for writing Area Chairs (or Editors) of Machine Learning Conferences and... Continue
We briefly review the two classical problems of distribution estimation and identity testing (in the context of property testing), then propose to extend them to a Markovian setting. We will see that the sample complexity... Continue
In our previous post, we derived a natural-gradient variational inference (NGVI) algorithm for neural networks, detailing all our approximations and providing intuition. We saw it converge faster than more naive variational inference algorithms on relatively... Continue
Bayesian Deep Learning hopes to tackle neural networks’ poorly-calibrated uncertainties by injecting some level of Bayesian thinking. There has been mixed success: progress is difficult as scaling Bayesian methods to such huge models is difficult!... Continue
A very old and yet very exciting problem in statistics is the definition of a universal estimator $\hat{\theta}$. An estimation procedure that would work all the time. Close your eyes, push the button, it works,... Continue
Here we list research code that has been open-sourced to accompany recent publications. Also see our team's github page.