We thank the reviewers for the positive feedback and their interest in our work! Below we address some questions. Both algorithms are well-tuned for hyperparameters. We didn't include it in the submission because after all the We will make sure to define them earlier in the paper in the revision. We are happy to clarify them.

Y es, the total complexity is proportional to the number of aggregated tasks. Add experiments to compare ANIL and MAML and w.r .t. the size B of samples: Why sample size in inner-loop is not taken into analysis, as Fallah et al. [4] does: This setting has also been considered in Rajeswaran et al. [24], Ji et al. [13]. Reviewer 2: Dependence on κ. iMAML depends on κ in contrast to poly (κ) of this work: Add an experiment to verify the tightness: Great point! W e will definitely add such an experiment in the revision. W e will clarify it in the revision.

R1: We do agree that our approach is complex and involves "multiple approximation steps". C2: On Park1, the NN "finds the global optimum after one query point"-- How is this significant... " First, the quality of the query point very much depends on the accuracy of the surrogate model. C3: Details about hyper-parameter selection; no liberty to choose a heldout dataset in practice. We optimized the hyper-parameters to minimize the average test error. We will supplement these details.

If their analysis tricks do improve PG guarantees, how does it compare then? Reviewer 2: Q1: It would be interesting to complement the theoretical results with empirical results in toy problem. We are working on experiments and will add these results to the revision. Q2: For the error term that disappears with a larger mini-batch (line 211). A2: Y es, this error term should be called as variance error.

We thank the reviewers for the positive feedback and their interest in our work! Below we address some questions. Both algorithms are well-tuned for hyperparameters. We didn't include it in the submission because after all the We will make sure to define them earlier in the paper in the revision. We are happy to clarify them.

Y es, the total complexity is proportional to the number of aggregated tasks. Add experiments to compare ANIL and MAML and w.r .t. the size B of samples: Why sample size in inner-loop is not taken into analysis, as Fallah et al. [4] does: This setting has also been considered in Rajeswaran et al. [24], Ji et al. [13]. Reviewer 2: Dependence on κ. iMAML depends on κ in contrast to poly (κ) of this work: Add an experiment to verify the tightness: Great point! W e will definitely add such an experiment in the revision. W e will clarify it in the revision.

What can marketers bring to the mix when AI is so powerful? Don't miss a MarketingProfs podcast, subscribe to our free newsletter! Passion, for one thing, says Peter Prodromou of Boathouse. "If you're in the upper right-hand corner with passion, chances are people are going to want to work with you or buy your product," he says on the latest episode of Marketing Smarts. "Think about Apple and Tesla; those are two brands that are very much about passion. Your ability to convey that is critically important." AI is just an algorithm, after all. "Everybody is going to shop at Amazon because they have the best algorithm, and there may or may not be passion for it," Peter says.

This is a Women in AI Podcast transcript, for this interview we have Wendy Gonzalez, CEO at Sama, speaking with us about high-quality data training and what she's getting up to in her current role. We hope you enjoy the episode. Listen to the podcast here. So today I'm joined by Wendy Gonzalez on our Women in AI podcast episode, who is the Interim CEO of Sama, and I'm really excited to speak to her today. Hi, Wendy, how are you?

WIRED has challenged computer scientist and Hidden Door cofounder and CEO Hilary Mason to explain machine learning to 5 different people; a child, teen, a college student, a grad student and an expert.

Artificial intelligence (AI) and machine-learning (ML) have quickly grown beyond a few major tech companies and hardcore academic researchers. Every marketing organization can tap into the power of AI to streamline operations and grow the business. The new book The AI Marketing Canvas: A Five-Stage Road Map to Implementing Artificial Intelligence in Marketing provides a growth framework for business and marketing leaders to implement AI using a five-stage model called the "AI Marketing Canvas." On this episode of Marketing Smarts, I speak with co-author Rajkumar Venkatesan about how he and his co-writer developed those stages by studying leading global brands. We cover examples of brands―including Google, Lyft and Coca-Cola―that have successfully woven AI into their marketing strategies. This is not a conversation about coding for AI models. Raj and I talk about how marketing leaders can go from "zero to hero" with AI in marketing, and what that means for your team and your company culture. Listen to the entire show now from the link above, or download the mp3 and listen at your convenience.