In June, Mark Zuckerberg went for the ultimate Hail Mary in the ever-intensifying AI race: He spun up a brand-new Meta AI lab after making a $14.3 billion acquisition of Scale AI - and then spending billions more hiring some of the industry's preeminent researchers and engineers. Fast-forward a couple of months, and Zuckerberg may […]
From VOC to JSON: Importing pre-annotations made simple The post How to Import Pre-Annotated Data into Label Studio and Run the Full Stack with Docker appeared first on Towards Data Science.
For a smooth-running smart home with a simple setup, the Eero Pro 7 mesh is a Wi-Fi 7 upgrade worth considering.
Lenovo is gearing up to show off its latest products at Europe’s IFA tech tradeshow next week, but leaks may have just given us a first look at what’s being announced. The most notable gadget shared by reputable leaker Evan Blass shows an image of a concept laptop design with a display that rotates between […]
This seems to be the year that Google's AI features are actually starting to add up to something useful. After a week testing the Pixel 10 Pro, my colleagues Allison Johnson and Vee Song say some of the new features are legitimately useful - at least when they work, which isn't always as expected. Case […]
Get 20% off with a Dyson coupon code, plus save up to $200 on vacuums, Airwraps, and more.
arXiv:2508.08606v2 Announce Type: replace-cross Abstract: Federated Learning (FL), as a distributed collaborative Machine Learning (ML) framework under privacy-preserving constraints, has garnered increasing research attention in cross-organizational data collaboration scenarios. This paper proposes a class of distributed optimization algorithms based on the augmented Lagrangian technique, designed to accommodate diverse communication topologies in both centralized and decentralized FL settings. Furthermore, we develop multiple termination criteria and parameter update mechanisms to enhance computational efficiency, accompanied by rigorous theoretical guarantees of convergence. By generalizing the augmented Lagrangian relaxation through the incorporation of proximal relaxation and quadratic approximation, our framework systematically recovers a broad of classical unconstrained optimization methods, including proximal algorithm, classic gradient descent, and stochastic gradient descent, among others. Notably, the convergence properties of these methods can be naturally derived within the proposed theoretical framework. Numerical experiments demonstrate that the proposed algorithm exhibits strong performance in large-scale settings with significant statistical heterogeneity across clients.
arXiv:2508.20326v1 Announce Type: new Abstract: Stochastic gradient optimization is the dominant learning paradigm for a variety of scenarios, from classical supervised learning to modern self-supervised learning. We consider stochastic gradient algorithms for learning problems whose objectives rely on unknown nuisance parameters, and establish non-asymptotic convergence guarantees. Our results show that, while the presence of a nuisance can alter the optimum and upset the optimization trajectory, the classical stochastic gradient algorithm may still converge under appropriate conditions, such as Neyman orthogonality. Moreover, even when Neyman orthogonality is not satisfied, we show that an algorithm variant with approximately orthogonalized updates (with an approximately orthogonalized gradient oracle) may achieve similar convergence rates. Examples from orthogonal statistical learning/double machine learning and causal inference are discussed.
Large language models (LLMs) now stand at the center of countless AI breakthroughs—chatbots, coding assistants, question answering, creative writing, and much more. But despite their prowess, they remain stateless: each query arrives with no memory of what came before. Their fixed context windows mean they can’t accumulate persistent knowledge across long conversations or multi-session tasks, […] The post Memory-R1: How Reinforcement Learning Supercharges LLM Memory Agents appeared first on MarkTechPost.
arXiv:2508.20102v1 Announce Type: cross Abstract: Signal control in urban corridors faces the dual challenge of maintaining arterial traffic progression while adapting to demand variations at local intersections. We propose a hierarchical traffic signal coordination and control scheme that integrates model-based optimization with reinforcement learning. The system consists of: (i) a High-Level Coordinator (HLC) that selects coordination strategies based on observed and predicted demand; (ii) a Corridor Coordinator that derives phase constraints from the selected strategy-either Max-Flow Coordination (MFC) or Green-Wave Coordination (GWC); and (iii) Hybrid Signal Agents (HSAs) that determine signal phases via reinforcement learning with action masking to enforce feasibility. Hierarchical reinforcement learning with Proximal Policy Optimization (PPO) is used to train HSA and HLC policies. At the lower level, three HSA policies-MFC-aware, GWC-aware, and pure agent control (PAC) are trained in conjunction with their respective coordination strategies. At the higher level, the HLC is trained to dynamically switch strategies using a multi-objective reward balancing corridor-level and network-wide performance. The proposed scheme was developed and evaluated on a SUMO-RLlib platform. Case results show that hybrid MFC maximizes throughput under heavy demand; hybrid GWC consistently minimizes arterial stops and maintains progression across diverse traffic conditions but can reduce network-wide efficiency; and PAC improves network-wide travel time in moderate demand but is less effective under heavy demand. The hierarchical design enables adaptive strategy selection, achieving robust performance across all demand levels.
