Weintroduceaweak versionofexp-concavity; see Assumption (A2). Let 0 2 0 beapointinthegrid 0 minimizing D( , 0).

Successful adoption of deep learning (DL) in the wild requires models to be: (1) compact, (2) accurate, and (3) robust to distributional shifts. Unfortunately, efforts towards simultaneously meeting these requirements have mostly been unsuccessful. This raises an important question: Is the inability to create Compact, Accurate, and Robust Deep neural networks (CARDs) fundamental? To answer this question, we perform a large-scale analysis of popular model compression techniques which uncovers several intriguing patterns. Notably, in contrast to traditional pruning approaches (e.g., fine tuning and gradual magnitude pruning), we find that ``lottery ticket-style'' approaches can surprisingly be used to produce CARDs, including binary-weight CARDs. Specifically, we are able to create extremely compact CARDs that, compared to their larger counterparts, have similar test accuracy and matching (or better) robustness---simply by pruning and (optionally) quantizing. Leveraging the compactness of CARDs, we develop a simple domain-adaptive test-time ensembling approach (CARD-Decks) that uses a gating module to dynamically select appropriate CARDs from the CARD-Deck based on their spectral-similarity with test samples.

WIRED Money takes place in Studio Spaces, London on May 18, 2017. For more details and to purchase your ticket visit wiredevent.co.uk "Breaking: Two Explosions in the White House and Barack Obama is injured." At the time of the tweet, AP's account had around two million followers. The post was favourited, retweeted, and spread. At 13:13, AP confirmed the tweet was fake.

A computer program that uses AI planning techniques is now the world champion computer program in the game of Contract Bridge. As reported in The New York Times and The Washington Post, this program--a new version of Great Game Products' The classical approach used in AI programs for games of strategy is to do a game tree search using the well-known minimax formula (eq. 1) The minimax computation is basically a bruteforce search: If implemented as formulated here, it would examine every node in the game tree. In practical implementations of minimax game tree searching, a number of techniques are used to improve the efficiency of this computation: putting a bound on the depth of the search, using alpha-beta pruning, doing transposition-table lookup, and so on. However, even with enhancements such as these, minimax computations often involve examining huge numbers of nodes in the game tree. Because a Bridge hand is typically played in just a few minutes, there is not enough time for a game tree search to search enough of this tree to make good decisions.