Prediction algorithms, such as deep neural networks (DNNs), are used in many domain sciences to directly estimate internal parameters of interest in simulator-based models, especially in settings where the observations include images or complex high-dimensional data. In parallel, modern neural density estimators, such as normalizing flows, are becoming increasingly popular for uncertainty quantification, especially when both parameters and observations are high-dimensional. However, parameter inference is an inverse problem and not a prediction task; thus, an open challenge is to construct conditionally valid and precise confidence regions, with a guaranteed probability of covering the true parameters of the data-generating process, no matter what the (unknown) parameter values are, and without relying on large-sample theory. Many simulator-based inference (SBI) methods are indeed known to produce biased or overly confident parameter regions, yielding misleading uncertainty estimates. This paper presents WALDO, a novel method to construct confidence regions with finite-sample conditional validity by leveraging prediction algorithms or posterior estimators that are currently widely adopted in SBI. WALDO reframes the well-known Wald test statistic, and uses a computationally efficient regression-based machinery for classical Neyman inversion of hypothesis tests. We apply our method to a recent high-energy physics problem, where prediction with DNNs has previously led to estimates with prediction bias. We also illustrate how our approach can correct overly confident posterior regions computed with normalizing flows.

Max Holloway claims that for the sake of self-motivation he needs to summon short-term memory loss about his June 3 knockout victory over Jose Aldo. "I have no idea what you're talking about. I have to be Dory," Holloway says, referring to the forgetful "Finding Nemo" character. After Holloway (18-3) landed 128 strikes to Aldo's 56 to become featherweight champion by third-round knockout in Aldo's home country of Brazil, the new champion has to meet Aldo (26-3) again Saturday night in the main event of the UFC 218 pay-per-view card. I know I'm coming with new tricks," Holloway, 25, told the Los Angeles Times this week. A new me, a new him and I can't wait to do this thing. I'm getting ready for the best Aldo, but I hope he better be ready for the best me. "It's a passing of the torch, and I'm going to be running with it for a long time." Aldo has claimed "this fight's going to be different" after he wasn't feeling right before the loss, but has "now recovered," prompting Hawaii's Holloway to respond, "You can't lie when you get in there." Aldo stepped in for Holloway's scheduled opponent, Frankie Edgar, when Edgar was fallen by an injury. The UFC's longtime featherweight champion surrendered the belt in a quick 2015 knockout loss to current lightweight champion Conor McGregor before defeating Edgar last year. Asked if he believes if this is his final chance to reunite with the belt, Aldo said, "No, but I will write a different story this time and get my title back.

If Salesforce delivers artificial intelligence as part and parcel of everyday business applications as promised, its customers are ready to use it, at least according to an informal and very unscientific survey. AI is a class of technology that teaches itself how to perform tasks. In one form, AI can learn to act as a personal assistant to its human users. But to date, much of the available AI technology has been expensive and hard to implement. At the company's annual Dreamforce event in San Francisco, Salesforce crm chief executive Marc Benioff and other execs again talked up the company's plan to integrate AI into its various sales, marketing, e-commerce, and customer service software products.