Although the provided novel algorithm looks impressive both from the theoretical prospective and in the experimental comparison, its substantiation has quite some room for improvement. The major point is the proof of Theorem 1: - it is unclear how the proof of the theorem follows from Lemmas 3 and 4, since none of these lemmas is related to the optimal solution of the considered diversity problem. I assume that the missing proposition is the one, which would establish connection between the considered linear program in lines 153-154 (by the way, it is very uncomfortable that the main formulation is not numbered and therefore can not be easily referenced) and the diversity problem. I believe that this connection may have the following format: if the linear program is equipped with integrality constraints (which is, all variables x_{ir}\in {0,1}), the resulting ILP is equivalent to the considered diversity problem. Indeed, the proof of such a proposition is not obvious for me as well.

The pioneering method for unsupervised meta-learning, CACTUs, is a clustering-based approach with pseudo-labeling. This approach is model-agnostic and can be combined with supervised algorithms to learn from unlabeled data. However, it often suffers from label inconsistency or limited diversity, which leads to poor performance. In this work, we prove that the core reason for this is lack of a clustering-friendly property in the embedding space. We address this by minimizing the inter- to intra-class similarity ratio to provide clustering-friendly embedding features, and validate our approach through comprehensive experiments. Note that, despite only utilizing a simple clustering algorithm (k-means) in our embedding space to obtain the pseudo-labels, we achieve significant improvement. Moreover, we adopt a progressive evaluation mechanism to obtain more diverse samples in order to further alleviate the limited diversity problem. Finally, our approach is also model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in two tasks.

First of all, the peer-review process is broken. Every fourth NeurIPS submission is put on arXiv. There are DeepMind researchers publicly going after reviewers who are criticizing their ICLR submission. On top of that, papers by well-known institutes that were put on arXiv are accepted at top conferences, despite the reviewers agreeing on rejection. In contrast, vice versa, some papers with a majority of accepts are overruled by the AC.

Over the last few decades, research, activity, and funding have been devoted to improving the recruitment, retention, and advancement of women in the fields of science, engineering, and medicine. In recent years the diversity of those participating in these fields, particularly the participation of women, has improved and there are significantly more women entering careers and studying science, engineering, and medicine than ever before. However, as women increasingly enter these fields they face biases and barriers and it is not surprising that sexual harassment is one of these barriers. According to the National Academies of Sciences, Engineering, and Medicine 2018, report, the count of women in science is decreasing since 1990. The report also revealed that till 2015, women made up only 18% of computer science majors in the US -- a decline from a high of 37% in 1984.

The tech industry has a diversity problem, that's nothing new. However, this diversity problem has damaging implications for the future of artificial intelligence development, argues World Economic Forum AI and machine learning head Kay Firth-Butterfield. Speaking at an event in Tianjin, China, Firth-Butterfield flagged the issue of bias within AI algorithms, calling on the need to make the industry "much more diverse" in the West. "There have been some obvious problems with AI algorithms," she told CNBC, mentioning a case that occurred in 2015, when Google's image-recognition software labelled a black man and his friend as'gorillas'. According to a report published earlier this year by Wired, Google has yet to properly fix this issue – opting instead to simply block search terms for primates.

For all their differences, big tech companies agree on where we're heading: into a future dominated by smart machines. Google, Amazon, Facebook, and Apple all say that every aspect of our lives will soon be transformed by artificial intelligence and machine learning, through innovations such as self-driving cars and facial recognition. Yet the people whose work underpins that vision don't much resemble the society their inventions are supposed to transform. WIRED worked with Montreal startup Element AI to estimate the diversity of leading machine learning researchers, and found that only 12 percent were women. That estimate came from tallying the numbers of men and women who had contributed work at three top machine learning conferences in 2017.

For all their differences, big tech companies agree on where we're heading: into a future dominated by smart machines. Google, Amazon, Facebook, and Apple all say that every aspect of our lives will soon be transformed by artificial intelligence and machine learning, through innovations such as self-driving cars and facial recognition. Yet the people whose work underpins that vision don't much resemble the society their inventions are supposed to transform. WIRED worked with Montreal startup Element AI to estimate the diversity of leading machine learning researchers, and found that only 12 percent were women. That estimate came from tallying the numbers of men and women who had contributed work at three top machine learning conferences in 2017.

For all their differences, big tech companies agree on where we're heading: into a future dominated by smart machines. Google, Amazon, Facebook, and Apple all say that every aspect of our lives will soon be transformed by artificial intelligence and machine learning, through innovations such as self-driving cars and facial recognition. Yet the people whose work underpins that vision don't much resemble the society their inventions are supposed to transform. WIRED worked with Montreal startup Element AI to estimate the diversity of leading machine learning researchers, and found that only 12 percent were women. That estimate came from tallying the numbers of men and women who had contributed work at three top machine learning conferences in 2017.

It's often been said that successful entrepreneurs don't just start businesses; they solve problems. Amazon simplified online buying and selling. Uber and Lyft made transportation easy and reliable.

After going through Y Combinator, the prestigious Silicon Valley accelerator program that's produced tech darlings like Dropbox, Airbnb and Coinbase, Masood and her co-founder and CTO, Syed Ahmed, pivoted their business model. The company that emerged was TARA.AI, an Artificial Intelligence …