We introduce a model for neural scaling laws under sparse activations. In the model, test loss is often dominated by rare coordinates that are never observed in the training input. This mechanism induces a novel bottleneck absent from dense models. We derive the asymptotic population loss in both the underparameterized and overparameterized regimes, and show that the loss exhibits a double-descent peak near the interpolation threshold -- where the number of parameters is just sufficient to fit the training data -- resulting in a loss curve governed by two distinct scaling exponents -- one for the overparameterized regime and one for the underparameterized regime -- with a gap determined by the degree of sparsity. Additionally, we derive a compute-optimal frontier that favors increasing dataset size over model capacity under fixed compute budgets. We also analyze gradient-descent dynamics and identify a scaling law for the probability that fixed-step gradient descent becomes unstable. We further show that the sparsity-induced effect persists under nonlinear activations.

We introduce training-free looped transformers, in which a lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen checkpoint without additional fine-tuning, continued training, or architectural changes. Unlike prior looped transformer methods that train with the looped structure end-to-end, we retrofit recurrence onto pretrained models at test time. We show that naive block reapplication usually degrades performance, highlighting the importance of the loop application strategy. Motivated by viewing a pre-norm transformer block as a forward Euler step on an ODE, we instead treat looping as a refinement of the same approximation, replacing one large update with smaller damped sub-steps. Across seven dense, sparse MoE, and MLA+MoE model families, our method improves Qwen3-4B-Instruct by +2.64 pp on MMLU-Pro, Qwen3-30B-A3B-Instruct by +1.14 pp on CommonsenseQA, and Moonlight-16B-A3B-Instruct by +1.20 pp on OpenBookQA.

I avoid AI tools because thinking is supposed to be hard. It's what makes us human Long before the age of multi-billion-dollar AI companies promising to disrupt the field of software development, I was learning to code the hard way. It was the mid-2000s, and I was a child with unmonitored access to the family computer. With the help of a basic text editor program, I learned how to make websites - first basic, then increasingly complex - from scratch. The results were never as beautiful or polished as in my imagination, but I could live with that, because I was learning a craft. The painstaking hours of debugging and poring over arcane documentation for projects that I eventually abandoned never felt wasted.

There's Never Been a Better Time to Study Computer Science Even as AI progresses, coders aren't doomed. It's a weird time to be studying computer science. Recent grads have a higher unemployment rate than those in just about every other major--yes, even philosophy. The internet is littered with rants from newly minted programmers who can't find work. On one such YouTube video, the top comment reads: "Your first mistake is not being born earlier."

Minka Kelly uncorks a heater at 45, ABS backfires spectacularly and LSU parents vs a security guard! Robot's lifeless corpse hauled off stage after fall during disastrous Michael Jackson impression Bear cubs spar on woman's front porch in adorable viral nature video, reactions pour in Show Tiffany Stratton some respect -- a boob job doesn't mean the WWE champ is made of plastic Britney Spears stuns with a post-plea deal Instagram dance, college baseball HOT mic & is this dream normal? Landlord in a tenant's home for repairs was caught on a security camera getting it on with a woman instead Paige Spiranac continues her generational golf content influencing run in 2026, Mike Alstott is ripped & MEAT! 'World's sexiest fan' drops her World Cup anthem and here's why you never assist a bike thief Wearing only a watch, a headlamp and flip-flops isn't a great disguise when trashing a neighbor's motion light Stephen Miller: The American people rejected'third world' Democratic policies by voting for Trump Former CENTCOM commander'concerned' about Iran's residual military capabilities Wall Street titans sound alarm on Mamdani's'reckless' targeting of top employers Retired general says Iran is fighting a'war of resistance' Kevin Warsh's potential Fed chairmanship sparks economic debate on inflation Minnesota fraud mastermind sentenced to 41.5 years in prison OutKick-Culture Selena Gomez is reportedly bringing her talents to award-winning director's new four-hour X-rated movie Don't let reports that Selena Gomez is going to be starring in an X-rated movie fool you. This isn't going to be a poorly produced amateur-level movie thrown together with someone who doesn't know what they're doing. It's also not a sex tape, for the folks who can't get their act together.

Selena Gomez is reportedly bringing her talents to award-winning director's new four-hour X-rated movie Minka Kelly uncorks a heater at 45, ABS backfires spectacularly and LSU parents vs a security guard! Robot's lifeless corpse hauled off stage after fall during disastrous Michael Jackson impression Bear cubs spar on woman's front porch in adorable viral nature video, reactions pour in Show Tiffany Stratton some respect -- a boob job doesn't mean the WWE champ is made of plastic Britney Spears stuns with a post-plea deal Instagram dance, college baseball HOT mic & is this dream normal? Landlord in a tenant's home for repairs was caught on a security camera getting it on with a woman instead Paige Spiranac continues her generational golf content influencing run in 2026, Mike Alstott is ripped & MEAT! 'World's sexiest fan' drops her World Cup anthem and here's why you never assist a bike thief Wearing only a watch, a headlamp and flip-flops isn't a great disguise when trashing a neighbor's motion light Stephen Miller: The American people rejected'third world' Democratic policies by voting for Trump Former CENTCOM commander'concerned' about Iran's residual military capabilities Wall Street titans sound alarm on Mamdani's'reckless' targeting of top employers Retired general says Iran is fighting a'war of resistance' Kevin Warsh's potential Fed chairmanship sparks economic debate on inflation Minnesota fraud mastermind sentenced to 41.5 years in prison President Tiffany Hernandez said the school was'using a new AI system as our reader' and called it'a lesson learned' Kurt Knutsson discusses growing public backlash against AI, including former Google CEO Eric Schmidt being booed at a University of Arizona commencement. He further discusses the development of artificial eggs that could revive dead species. I'll be honest with you guys, I don't know what to make of my feelings toward artificial intelligence, because my mood on the subject changes by the day.

Learning-to-Defer (L2D) methods route each query either to a predictive model or to external experts. While existing work studies this problem in batch settings, real-world deployments require handling streaming data, changing expert availability, and shifting expert distribution. We introduce the first online L2D algorithm for multiclass classification with bandit feedback and a dynamically varying pool of experts. Our method achieves regret guarantees of $O((n+n_e)T^{2/3})$ in general and $O((n+n_e)\sqrt{T})$ under a low-noise condition, where $T$ is the time horizon, $n$ is the number of labels, and $n_e$ is the number of distinct experts observed across rounds. The analysis builds on novel $\mathcal{H}$-consistency bounds for the online framework, combined with first-order methods for online convex optimization. Experiments on synthetic and real-world datasets demonstrate that our approach effectively extends standard Learning-to-Defer to settings with varying expert availability and reliability.

Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this paper, we study a bandit problem where the payoffs of arms are smooth on a graph. This framework is suitable for solving online learning problems that involve graphs, such as content-based recommendation. In this problem, each recommended item is a node and its expected rating is similar to its neighbors. The goal is to recommend items that have high expected ratings. We aim for the algorithms where the cumulative regret would not scale poorly with the number of nodes. In particular, we introduce the notion of an effective dimension, which is small in real-world graphs, and propose two algorithms for solving our problem that scale linearly in this dimension. Our experiments on real-world content recommendation problem show that a good estimator of user preferences for thousands of items can be learned from just tens nodes evaluations.

Communication is a major bottleneck in distributed learning, especially in large-scale settings and in federated learning environments with slow links. Three standard ways to reduce this cost are communication compression, local training, and communication-computation overlap. Methods that combine these ingredients are used in practice and have been found to be effective for large-scale training, but there is little theory for methods that combine all three. We study a heterogeneous-compute setting in which different workers may take different numbers of local steps, and we propose LOSCAR-SGD, a Local SGD method that communicates only a sparse subset of model coordinates and continues optimizing while communication is in flight. A key ingredient is a delay-corrected merge rule that incorporates delayed synchronized information without discarding the progress made during the overlap phase. We give convergence guarantees for smooth non-convex objectives and show how sparsity, overlap, and worker heterogeneity affect the rate. To the best of our knowledge, this is the first theory for this combination of ingredients. Experiments further show that communication-computation overlap reduces training time and that the delay-corrected merge outperforms naive overwriting.

Things to Do in L.A. Tap to enable a layout that focuses on the article. Children and parents at a recent L.A. Unified school board meeting where screen-time limits were discussed. This is read by an automated voice. Please report any issues or inconsistencies here . The L.A. Board of Education got its first look at proposed screen-time limits for students, including a total ban until secnd grade.