Online Convex Optimization
PulseAugur coverage of Online Convex Optimization — every cluster mentioning Online Convex Optimization across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New algorithm tackles adaptive online learning with time-varying costs
Researchers have developed a new algorithm for Online Convex Optimization (OCO) that addresses time-varying movement costs and delayed feedback. This novel approach offers improved data-dependent regret bounds for arbit…
-
New algorithm tackles heavy-tailed noise in online convex optimization
Researchers have developed a new method for online convex optimization that can handle heavy-tailed noise without requiring prior knowledge of the noise's properties. The proposed algorithm achieves a regret bound that …
-
New arXiv papers explore advanced online optimization techniques · 3 sources tracked
Three new research papers published on arXiv explore advanced optimization techniques in machine learning. The first paper details sharp oracle-regret tradeoffs for projection-free online convex optimization, providing …
-
New research tackles dynamic regret in online learning with novel methods · 3 sources tracked
Three new research papers explore dynamic regret minimization in online learning settings. The first paper focuses on Follow-the-Regularized-Leader (FTRL) methods for curved losses and adaptive optimizers like Adam, pre…
-
Minimax Alternating Regret for Experts Problem and OCO Resolved · 2 sources tracked
Researchers have resolved the minimax regret rate for the Experts Problem and Online Convex Optimization (OCO). For the d-expert problem, the minimax alternating regret is shown to be $\Theta(\log d)$, independent of th…
-
New method tackles online convex optimization with pairwise feedback
Researchers have introduced a novel approach to online convex optimization that utilizes dueling (pairwise comparison) feedback. This method converts the binary preference data into approximate gradients, allowing the a…
-
New method ensures real-time safety for critical IoT systems
A new paper introduces OCO-PAoI-Hard, a method for ensuring real-time safety in critical IoT systems by guaranteeing that the Age of Information (AoI) stays below a hard deadline. This approach addresses limitations of …
-
New theory achieves logarithmic high-probability regret in online convex optimization
Researchers have developed a new theoretical framework for online convex optimization (OCO) that achieves logarithmic high-probability regret. This advancement addresses the challenge of learning with limited feedback, …
-
New Principle Achieves Optimal Online Inventory Optimization
Researchers have developed a novel principle for online inventory optimization (OIO) that achieves optimal performance on general convex sets. This method, which involves maintaining a hidden target and projecting it on…
-
New arXiv Papers Detail Advances in Convex Optimization Techniques
Two new research papers on arXiv explore advancements in convex optimization. The first paper introduces a unified probing model for Online Convex Optimization (OCO) that can improve worst-case regret even with a sublin…
-
AI agents tackle temporal regret and dynamic optimization challenges
Two new research papers explore advanced methods for improving AI agent decision-making and learning. The first paper, "Trivium," introduces temporal regret as a key objective for causal-memory controllers, aiming to lo…
-
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…