Estimating uncertainty in a model's predictions is important, as

We consider stochastic settings for clustering, and develop provably-good (approximation) algorithms for a number of these notions.

Neural Information Processing Systems http://nips.cc/

Solomonoff's general theory of inference (Solomonoff, 1964) and the Minimum Description Length principle (Grünwald, 2007; Rissanen, 2007) formalize Occam's razor, and hold that a good model of data is a model that is good at losslessly compressing the data, including the cost of describing the model itself. Deep neural networks might seem to go against this principle given the large number of parameters to be encoded. We demonstrate experimentally the ability of deep neural networks to compress the training data even when accounting for parameter encoding. The compression viewpoint originally motivated the use of variational methods in neural networks (Hinton and V an Camp, 1993; Schmidhuber, 1997). Unexpectedly, we found that these variational methods provide surprisingly poor compression bounds, despite being explicitly built to minimize such bounds. This might explain the relatively poor practical performance of variational methods in deep learning. On the other hand, simple incremental encoding methods yield excellent compression values on deep networks, vindicating Solomonoff's approach.

Neural Information Processing Systems http://nips.cc/

Unlike previous approaches that assume unconfoundedness, i.e., no unobserved confounders affected both treatment assignment and outcomes, we calibrate policy learning for realistic violations of this unverifiable assumption with uncertainty sets motivated by sensitivity analysis in causal inference. Our framework for confounding-robust policy improvement optimizes the minimax regret of a candidate policy against a baseline or reference "status quo" policy, over an uncertainty set around nominal propensity weights.

Causal graphs [e.g., Pearl, 2009, Spirtes et al., 2000] allow us to reason about this in a principled way when the domains correspond to different external interventions on the system, or

We study a safe reinforcement learning problem in which the constraints are defined as the expected cost over finite-length trajectories.

As a result, depth-limited search algorithms used in single-agent settings and perfect-information games do not apply.

Multi-party machine learning allows several parties (e.g., hospitals, banks, government agencies) to