How the artists in this year's survey do or, more often, don't acknowledge those who paved the way for them. Machado makes pieces that one might call documents of reverence, excavated burial grounds. If nothing else, the 2026 Whitney Biennial, curated by Marcela Guerrero and Drew Sawyer (at the Whitney Museum through August 23rd), introduces viewers to what I call ChatGPT art--facsimiles of facsimiles by makers who have little if any relationship to what they're putting out there, aside from its being a product in service of a career. Indeed, it's difficult to think of the people who grew up with and apparently condone the use of A.I. sources in the creation of "art" as artists themselves, especially if you define art as a creative expression of thoughts or feelings that have changed, and contributed to the vision of, the artists who made it. It's true that, nearly from the beginning, postmodern art challenged the notion of originality, or, more specifically, the weight of originality--often with great joy and wit and not a little fear.

In this paper, we study the support recovery guarantees of underdetermined sparse regression using the `1-norm as a regularizer and a non-smooth loss function for data fidelity. More precisely, we focus in detail on the cases of `1 and ` losses, and contrast them with the usual `2 loss. While these losses are routinely used to account for either sparse (`1 loss) or uniform (` loss) noise models, a theoretical analysis of their performance is still lacking. In this article, we extend the existing theory from the smooth `2 case to these non-smooth cases. We derive a sharp condition which ensures that the support of the vector to recover is stable to small additive noise in the observations, as long as the loss constraint size is tuned proportionally to the noise level. A distinctive feature of our theory is that it also explains what happens when the support is unstable. While the support is not stable anymore, we identify an "extended support" and show that this extended support is stable to small additive noise. To exemplify the usefulness of our theory, we give a detailed numerical analysis of the support stability/instability of compressed sensing recovery with these different losses. This highlights different parameter regimes, ranging from total support stability to progressively increasing support instability.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

The Stochastic Block Model (SBM) is a widely used random graph model for networks with communities. Despite the recent burst of interest in community detection under the SBM from statistical and computational points of view, there are still gaps in understanding the fundamental limits of recovery. In this paper, we consider the SBM in its full generality, where there is no restriction on the number and sizes of communities or how they grow with the number of nodes, as well as on the connectivity probabilities inside or across communities. For such stochastic block models, we provide guarantees for exact recovery via a semidefinite program as well as upper and lower bounds on SBM parameters for exact recoverability. Our results exploit the tradeoffs among the various parameters of heterogenous SBM and provide recovery guarantees for many new interesting SBM configurations.

We present region-based, fully convolutional networks for accurate and efficient object detection. In contrast to previous region-based detectors such as Fast/Faster R-CNN [7, 19] that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image. To achieve this goal, we propose position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection. Our method can thus naturally adopt fully convolutional image classifier backbones, such as the latest Residual Networks (ResNets) [10], for object detection. We show competitive results on the PASCAL VOC datasets (e.g., 83.6% mAP on the 2007 set) with the 101-layer ResNet. Meanwhile, our result is achieved at a test-time speed of 170ms per image, 2.5-20 faster than the Faster R-CNN counterpart.

Neural Information Processing Systems http://nips.cc/

We consider the regime where nd. We propose randomized Newton-type algorithms that exploit non-uniform sub-sampling of { 2fi(w)}ni=1, as well as inexact updates, as means to reduce the computational complexity, and are applicable to a wide range of problems in machine learning. Two non-uniform sampling distributions based on block norm squares and block partial leverage scores are considered. Under certain assumptions, we show that our algorithms inherit a linear-quadratic convergence rate in w and achieve a lower computational complexity compared to similar existing methods. In addition, we show that our algorithms exhibit more robustness and better dependence on problem specific quantities, such as the condition number. We empirically demonstrate that our methods are at least twice as fast as Newton's methods on several real datasets.