Your Out-of-Distribution Detection Method is Not Robust!

Extreme multi-label classification (XMLC) is a problem of tagging an instance with a small subset of relevant labels chosen from an extremely large pool of possible labels. Large label spaces can be efficiently handled by organizing labels as a tree, like in the hierarchical softmax (HSM) approach commonly used for multi-class problems. In this paper, we investigate probabilistic label trees (PLTs) that have been recently devised for tackling XMLC problems. We show that PLTs are a no-regret multi-label generalization of HSM when precision@$k$ is used as a model evaluation metric. Critically, we prove that pick-one-label heuristic---a reduction technique from multi-label to multi-class that is routinely used along with HSM---is not consistent in general. We also show that our implementation of PLTs, referred to as extremeText (XT), obtains significantly better results than HSM with the pick-one-label heuristic and XML-CNN, a deep network specifically designed for XMLC problems. Moreover, XT is competitive to many state-of-the-art approaches in terms of statistical performance, model size and prediction time which makes it amenable to deploy in an online system.

The ocean’s bad boys don’t just cruise alone—they have preferred swimming partners.

Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of unsupervised learning of features correlated to specific labels in a dataset. We propose a VAE-based generative model which we show is capable of extracting features correlated to binary labels in the data and structuring it in a latent subspace which is easy to interpret. Our model, the Conditional Subspace VAE (CSVAE), uses mutual information minimization to learn a low-dimensional latent subspace associated with each label that can easily be inspected and independently manipulated. We demonstrate the utility of the learned representations for attribute manipulation tasks on both the Toronto Face and CelebA datasets.

Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data. Scaling up the training process of these models is crucial, but the most popular algorithm, Stochastic Gradient Descent (SGD), is a serial method that is surprisingly hard to parallelize. In this paper, we propose an efficient distributed stochastic optimization method by combining adaptivity with variance reduction techniques. Our analysis yields a linear speedup in the number of machines, constant memory footprint, and only a logarithmic number of communication rounds. Critically, our approach is a black-box reduction that parallelizes any serial online learning algorithm, streamlining prior analysis and allowing us to leverage the significant progress that has been made in designing adaptive algorithms. In particular, we achieve optimal convergence rates without any prior knowledge of smoothness parameters, yielding a more robust algorithm that reduces the need for hyperparameter tuning. We implement our algorithm in the Spark distributed framework and exhibit dramatic performance gains on large-scale logistic regression problems.

Nvidia unveiled DLSS 5 with 3D-Guided Neural Rendering at its GPU Technology Conference, using AI to add photorealistic lighting and materials to games in real-time. PCWorld reports this technology aims to bridge the gap between rendering and reality, enhancing details like skin and fabric in major titles including Hogwarts Legacy and Starfield. DLSS 5 launches this fall and represents what Nvidia calls a "GPT moment for graphics," potentially delivering unprecedented visual realism in PC gaming. We've only just gotten some of the headline features of DLSS 4.5, and now Nvidia has announced the next version. At its self-branded GPU Technology Conference in California, Nvidia revealed DLSS 5.

But growing up can help these famed Chesapeake crustaceans. Breakthroughs, discoveries, and DIY tips sent six days a week. Cannibalism is the number one killer of the crustaceans that congregate in mid-salinity waters like coastal estuaries. As a result, the blue crabs are relying on the safety of some threatened shallow water habitats, according to a study published today in the journal Proceedings of the National Academy of Science (). The lives of blue crabs are anything but boring.

The app reads your email inbox and your meeting calendar, then gives you a short audio summary. It can help you spend less time scrolling, but of course, there are privacy drawbacks to consider. WIRED is obsessed with what comes next. Through rigorous investigations and game-changing reporting, we tell stories that don't just reflect the moment--they help create it. When you look back in 10, 20, even 50 years, WIRED will be the publication that led the story of the present, mapped the people, products, and ideas defining it, and explained how those forces forged the future.

A quick inbox search may uncover unused online accounts still tied to your email and personal data, Kurt "CyberGuy" Knutsson writes for Fox News.

Where OpenAI's technology could show up in Iran Three places to watch, from the margins of war to the center of combat. It's been just over two weeks since OpenAI reached a controversial agreement to allow the Pentagon to use its AI in classified environments. There are still pressing questions about what exactly OpenAI's agreement allows for; Sam Altman said the military can't use his company's technology to build autonomous weapons, but the agreement really just demands that the military follow its own (quite permissive) guidelines about such weapons. OpenAI's other main claim, that the agreement will prevent use of its technology for domestic surveillance, appears equally dubious . It's not the first tech giant to embrace military contracts it had once vowed never to enter into, but the speed of the pivot was notable. Perhaps it's just about money; OpenAI is spending lots on AI training and is on the hunt for more revenue (from sources including ads).