From Jules Verne-inspired submarines to NASA-backed underwater habitats, the dream of an undersea civilization came closer than most people realize. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. Just as space exploration took off, ocean exploration faced some tragic setbacks. Breakthroughs, discoveries, and DIY tips sent six days a week. By signing up, you confirm you are 16+, will receive newsletters and promotional content and agree to our Terms of Use and acknowledge the data practices in our Privacy Policy .

Federated Learning (FL) is a distributed machine learning (ML) paradigm with collaboration among multiple clients without sharing data. FL is challenging under data heterogeneity and partial client participation. Learning sparse models is useful for communication and computational efficiency in FL, but it is especially difficult in the small-sample high-dimensional regime (d >> N) where optimization can yield parameter configurations that fail to generalize to unseen test data. While magnitude-based pruning doesn't account for uncertainty exploration in the parameter space, a formulation with probabilistic gates and an L0 constraint allows sampling from competing sparse configurations during training. In this work, we study entropy regularization of gate distributions as a mechanism to maintain uncertainty in sparse federated optimization by preventing early commitment to sparse support. We examine its impact under data heterogeneity, client participation heterogeneity, and sparsity. Experiments on synthetic and real-world benchmarks show consistent improvements over federated iterative hard thresholding (Fed-IHT) and pruning after dense federated averaging (FedAvg) training, both in statistical performance on test data and in sparsity recovery accuracy.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

Abstract--As black-box models become foundational to mod-solution that can be applied across a wide range of scientific ern research, ensuring their stability is paramount for the realiza-and industrial domains. The inherent diversity of inputs--ranging from structured Gaussian distributions to Notwithstanding its widespread application, the framework complex data with unknown structures--poses a significantexhibits certain shortcomings when dealing with complex challenge: how to stabilize black-box outputs while effectivelydatasets. First, standard resampling schemes often fail to leveraging available prior information. This paper introduces aaccount for the underlying data structures; as a result, the task-oriented randomization methodology that adaptively tailorsdrawn samples cannot reflect the true data distribution, thereby its strategy to the underlying generative mechanisms of the input data, specifically addressing unstructured complexities. Second, effective sampling requires prior comprehensive suite of stability guarantees is proposed. Beyondknowledge of the distribution, which is often unattainable establishing rigorous theoretical foundations for stability, thein practical environments.

Temperatures may be soaring, but there's an unseasonable chill on screens right now--at least when it comes to some of the movie offerings hitting streaming services this month. Director Yorgos Lanthimos delivers a twisted take on in on Netflix, while Shudder digs up painful family secrets and adds a side of demonic possession in If you fancy some summer scares that are a bit more Halloween-grade, Netflix also has a mesmerizing tour of a world of monsters and living nightmares, brought to life in stunning stop-motion. There are also plenty of retro delights surfacing on streamers this month that are more than worth a rewatch. Hulu reinstalls Spielberg's, which lands very differently in 2026; Criterion Channel is declassifying Sean Connery's first outings as 007, with, and coming to the specialist platform; and Prime Video brings all three films back to the future (sorry). Here are WIRED's picks of the best movies to watch right now.

Autonomous exploration in complex multi-agent reinforcement learning (MARL) with sparse rewards critically depends on providing agents with effective intrinsic motivation. While artificial curiosity offers a powerful self-supervised signal, it often confuses environmental stochasticity with meaningful novelty.

Occlusion is one of the fundamental challenges in crowd counting. In the community, various data-driven approaches have been developed to address this issue, yet their effectiveness is limited. This is mainly because most existing crowd counting datasets on which the methods are trained are based on passive cameras, restricting their ability to fully sense the environment. Recently, embodied navigation methods have shown significant potential in precise object detection in interactive scenes. These methods incorporate active camera settings, holding promise in addressing the fundamental issues in crowd counting.

The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this can be done by generating thinking traces before acting in the world. However, this process does not allow agents to acquire new information from the environment or adapt their behavior over time. In this work, we propose to scale test-time interaction, an untapped dimension of test-time scaling that increases the agent's interaction horizon to enable running rich behaviors such as exploration, backtracking, and dynamic re-planning within a single rollout. To demonstrate the promise of this scaling dimension, we study the domain of web agents.

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for large language model (LLM) alignment. This paper studies the setting of online RLHF and focuses on improving its sample efficiency. All existing algorithms for online RLHF, whether doing passive exploration or active exploration, suffer from a sample complexity that scales exponentially with the range of the reward function. This statistical inefficiency hinders their effectiveness in scenarios with heavily skewed preferences, e.g.

The remarkable empirical performance of distributional reinforcement learning (RL) has garnered increasing attention to understanding its theoretical advantages over classical RL. By decomposing the categorical distributional loss commonly employed in distributional RL, we find that the potential superiority of distributional RL can be attributed to a derived distribution-matching entropy regularization. This less-studied entropy regularization aims to capture additional knowledge of return distribution beyond only its expectation, contributing to an augmented reward signal in policy optimization. In contrast to the vanilla entropy regularization in MaxEnt RL, which explicitly encourages exploration by promoting diverse actions, the novel entropy regularization derived from categorical distributional loss implicitly updates policies to align the learned policy with (estimated) environmental uncertainty. Finally, extensive experiments verify the significance of this uncertainty-aware regularization from distributional RL on the empirical benefits over classical RL. Our study offers an innovative exploration perspective to explain the intrinsic benefits of distributional learning in RL.