Online Learning
PulseAugur coverage of Online Learning — every cluster mentioning Online Learning across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New algorithms enable LLM expert routing with limited feedback
Researchers have developed new algorithms for online learning with large language model (LLM) experts, specifically addressing scenarios with limited feedback. The proposed methods frame prompt routing to different LLM …
-
Online learning refines wind tunnel airflow for enhanced robot flight
Researchers have developed an online learning algorithm to precisely control airflow in a vertical wind tunnel for testing advanced aerial robots. This method combines a simplified physical model with iterative learning…
-
New framework tackles large-scale satellite scheduling with AI
Researchers have developed a new framework for tackling large-scale distributed constraint optimization problems (DCOPs), particularly for applications like satellite scheduling. The approach combines online learning al…
-
New bandit framework optimizes crowdsensing worker recruitment
Researchers have developed a new cost-aware bandit framework to optimize worker recruitment in mobile crowdsensing. This framework addresses the challenge of evolving worker performance, where individuals improve with e…
-
New learning rule enhances Echo State Networks for online self-supervised adaptation
Researchers have developed a novel perturbation-based learning rule for online self-supervised learning in Echo State Networks (ESNs). This new method addresses the tension between autonomous adaptation, online learning…
-
New framework tackles dynamic query selectivity estimation using online learning
Researchers have developed a new algorithmic framework for learning query selectivity in dynamic database and query workload environments. This approach, inspired by online learning, measures performance through regret,…
-
New research explores advanced multi-armed bandit algorithms · 8 sources tracked
This cluster features several research papers exploring advancements in multi-armed bandit algorithms. Topics include characterizing learnability in adversarial noisy bandits, developing contextual slate bandits with li…
-
New research explores leveraging action similarities in multi-armed bandit problems
A new research paper explores online learning strategies for multi-armed bandit problems where actions have inherent similarities, such as shared traits or hierarchical structures. The study introduces a rooted tree mod…
-
New paper proposes biologically inspired neuron model for efficient online learning
A new paper introduces a novel mechanistic model for multilayer neuronal networks that draws inspiration from biological computation. This model offers a practical alternative to traditional backpropagation, enabling ef…
-
New theory links polyhedral instability to online learning regret
Researchers have developed a new theoretical framework for understanding regret in online learning problems involving combinatorial actions. Their work introduces the concept of 'polyhedral instability,' which quantifie…