Yoshua Bengio

TL;DR: A survey of machine learning and combinatorial optimization problems can be found in this paper, where the main point is to see generic optimization problems as data points and inquire what is the relevant distribution of problems to use for learning on a given task.

TL;DR: In this paper, the authors examine some of the challenges of scaling deep learning algorithms to much larger models and datasets, reducing optimization difficulties due to ill-conditioning or local minima, designing more efficient and powerful inference and sampling procedures, and learning to disentangle the factors of variation underlying the observed data.

TL;DR: This work introduces several ways of regularizing the objective, which can dramatically stabilize the training of GAN models and shows that these regularizers can help the fair distribution of probability mass across the modes of the data generating distribution, during the early phases of training and thus providing a unified solution to the missing modes problem.

TL;DR: From smart grids to disaster management, high impact problems where existing gaps can be filled by ML are identified, in collaboration with other fields, to join the global effort against climate change.

TL;DR: A different attack on the problem is proposed, which deals with arbitrary (but noisy enough) corruption, arbitrary reconstruction loss, handling both discrete and continuous-valued variables, and removing the bias due to non-infinitesimal corruption noise.