Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss and its variants. In this paper, we generalize existing IoU-based losses to a new family of power IoU losses that have a power IoU term and an additional power regularization term with a single power parameter $\alpha$. We call this new family of losses the $\alpha$-IoU losses and analyze properties such as order preservingness and loss/gradient reweighting. Experiments on multiple object detection benchmarks and models demonstrate that $\alpha$-IoU losses, 1) can surpass existing IoU-based losses by a noticeable performance margin; 2) offer detectors more flexibility in achieving different levels of bbox regression accuracy by modulating $\alpha$; and 3) are more robust to small datasets and noisy bboxes.

We study the optimization problem associated with fitting two-layer ReLU neural networks with respect to the squared loss, where labels are generated by a target network. We make use of the rich symmetry structure to develop a novel set of tools for studying families of spurious minima. In contrast to existing approaches which operate in limiting regimes, our technique directly addresses the nonconvex loss landscape for finite number of inputs $d$ and neurons $k$, and provides analytic, rather than heuristic, information. In particular, we derive analytic estimates for the loss at different minima, and prove that, modulo $O(d^{-1/2})$-terms, the Hessian spectrum concentrates near small positive constants, with the exception of $\Theta(d)$ eigenvalues which grow linearly with~$d$. We further show that the Hessian spectrum at global and spurious minima coincide to $O(d^{-1/2})$-order, thus challenging our ability to argue about statistical generalization through local curvature. Lastly, our technique provides the exact \emph{fractional} dimensionality at which families of critical points turn from saddles into spurious minima. This makes possible the study of the creation and the annihilation of spurious minima using powerful tools from equivariant bifurcation theory.

We study the general problem of testing whether an unknown discrete distribution belongs to a specified family of distributions. More specifically, given a distribution family P and sample access to an unknown discrete distribution D, we want to distinguish (with high probability) between the case that D in P and the case that D is ε-far, in total variation distance, from every distribution in P . This is the prototypical hypothesis testing problem that has received significant attention in statistics and, more recently, in computer science. The main contribution of this work is a simple and general testing technique that is applicable to all distribution families whose Fourier spectrum satisfies a certain approximate sparsity property. We apply our Fourier-based framework to obtain near sample-optimal and computationally efficient testers for the following fundamental distribution families: Sums of Independent Integer Random Variables (SIIRVs), Poisson Multinomial Distributions (PMDs), and Discrete Log-Concave Distributions. For the first two, ours are the first non-trivial testers in the literature, vastly generalizing previous work on testing Poisson Binomial Distributions. For the third, our tester improves on prior work in both sample and time complexity.

This year, 16-year-old Joe Veneziale created a terrifying Old Hollywood hotel. Every October, 16-year-old Joe Veneziale builds a haunted house in his suburban Philadelphia neighborhood. The haunt is complete with live actors, intricate sets, and state-of-the-art tech. Breakthroughs, discoveries, and DIY tips sent every weekday. Joe Veneziale is known as the "Halloween guy" at his high school, and for good reason.

Four students have died after a school building collapsed in Indonesia on Monday, 99 others were taken to hospital but it is thought 38 people are still trapped. The BBC reports from a nearby centre where relatives face an anxious wait for any updates. Rescuers say they have been able to communicate with seven students and give them oxygen. Watch: Moments as 6.9 magnitude earthquake hit Philippines At least 69 people are killed after it struck on Tuesday night with officials declaring a state of calamity. Social media footage showed the massive crater in Thailand's capital leaving cars teetering on the edge.

The paper proposes a generalization of the KMeans Algorithm by introducing non-negative parameters alpha and beta. The motivation is that different instances of clustering problems may cluster well according to different clustering objectives. The optimal parameter configuration of alpha and beta defines an optimal choice, from the proposed family of clustering algorithms. The paper offers several theoretical contributions. It provides guarantees for the number of samples necessary such that the empirically best parameter set yields clustering costs is within epsilon bounds of the optimal parameters. It provides an algorithm for the enumeration of all possible sets of initial centers for any alpha-interval.

In the photograph, Anna Haidarzhy and her 4-month-old son, Tymofii, are barely visible under the bloodstained blanket. They lie in the rubble, at the feet of rescue workers in black and fluorescent uniforms. Just two arms, one from the mother, 31, one from her son, can be seen sticking out of the blanket. "It looked like they were saying goodbye," one of the rescuers, Serhii Mudrenko, said of the image. Their bodies were found in the smoking ruins of an apartment block hit in a Russian drone attack in March in the southern Ukrainian city of Odesa that killed 12 people.

Artificial intelligence refers to the development of computer systems that can perform tasks that typically require human intelligence, such as learning, problem-solving, perception, and decision-making.

Taryn Foster believes Australia's dying coral reefs can still be rescued--if she can speed up efforts to save them. For years, biologists like her have been lending a hand to reefs struggling with rising temperatures and ocean acidity: They've collected coral fragments and cut them into pieces to propagate and grow them in nurseries on land; they've crossbred species to build in heat-resistance; they've experimented with probiotics as a defense against deadly diseases. But even transplanting thousands of these healthy and upgraded corals onto damaged reefs will not be enough to save entire ecosystems, Foster says. "We need some way of deploying corals at scale." Sounds like a job for some robots.

But, as a famous fictional uncle once said, "with great power comes great responsibility." Once the people in your life find out you can fix some of their computer problems from the comfort of your couch, you may soon find yourself up to your eyeballs in tech support requests. Use this power wisely, and maybe set some boundaries.