Aug 27 2020
Speaker: Inderjit Dhillon3:00pm | Remote Access Only - see link below
Aug 25 2020
Speaker: Piotr Indyk12:30pm | Remote Access Only - see link below
Aug 20 2020
Speaker: Jason Eisner3:00pm | Remote Access Only - see link below
Aug 18 2020
Speaker: Li Deng12:30pm | Remote Access Only - see link below
Aug 13 2020
Speaker: John Langford3:00pm | Remote Access Only - see link below
There are three core orthogonal problems in reinforcement learning: (1) Crediting actions (2) generalizing across rich observations (3) Exploring to discover the information necessary for learning. Good solutions to pairs of these problems are fairly well known at this point, but solutions for...
Aug 11 2020
Speaker: John Shawe-Taylor12:30pm | Remote Access Only - see link below
Probably Approximately Correct (PAC) learning has attempted to analyse the generalisation of learning systems within the statistical learning framework. It has been referred to as a ‘worst case’ analysis, but the tools have been extended to analyse cases where benign distributions mean we can...
Aug 06 2020
Speaker: Eric Xing3:00pm | Remote Access Only - see link below
In handling wide range of experiences ranging from data instances, knowledge, constraints, to rewards, adversaries, and lifelong interplay in an ever-growing spectrum of tasks, contemporary ML/AI research has resulted in thousands of models, learning paradigms, optimization algorithms, not...
Aug 04 2020
Speaker: Aapo Hyvärinen12:30pm | Remote Access Only - see link below
Unsupervised learning, in particular learning general nonlinear representations, is one of the deepest problems in machine learning. Estimating latent quantities in a generative model provides a principled framework, and has been successfully used in the linear case, e.g. with independent...
Jul 30 2020
Efficient Robot Skill Learning via Grounded Simulation Learning, Imitation Learning from Observation, and Off-Policy Reinforcement Learning
Speaker: Peter Stone3:00pm | Remote Access Only - see link below
For autonomous robots to operate in the open, dynamically changing world, they will need to be able to learn a robust set of skills from relatively little experience. This talk begins by introducing Grounded Simulation Learning as a way to bridge the so-called reality gap between simulators and...
Jul 28 2020
Speaker: Arthur Gretton12:30pm | Remote Access Only - see link below
I will introduce Generalized Energy Based Models (GEBM) for generative modelling. These models combine two trained components: a base distribution (generally an implicit model), which can learn the support of data with low intrinsic dimension in a high dimensional...