Find a story

Search Spins

Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.

4 results for “contextual bandit”

SPIN Processed News Frame: The Hype

Reoptimization Algorithms for Contextual Bandits with Knapsack Constraints

A new theoretical algorithm for contextual bandits with knapsack constraints achieves a tighter regret bound of $O((\ln T)^3 / T)$, improving upon prior $O(1/\sqrt{T})$ bounds in related dynamic-pricing settings.

Spin 45% Claim Present in Source AI Risk Moderate
arXiv Machine Learning

Aug 13, 2026

SPIN Processed News Frame: The Hype

Progressive Content Refinement with Decaying Reward Joint LinUCB

Researchers introduced a new contextual bandit algorithm called Decaying Reward Joint LinUCB that models reward decay to prevent over-exploitation in LLM iterative refinement, showing improved performance on Sentiment Reversal and GSM8K benchmarks.

Spin 45% Claim Present in Source AI Risk Moderate
arXiv Computation and Language

Aug 10, 2026

SPIN Processed News Frame: The Hype

Bootstrap-Conditioned Action Selection with Tabular Foundation Models

Researchers propose BC-ICL, a method using frozen pre-trained tabular foundation models with bootstrap resampling and in-context learning to improve early-round decision-making performance in contextual bandits under sparse, biased, or cold-start data conditions.

Spin 35% Claim Present in Source AI Risk Moderate
arXiv Machine Learning

Aug 10, 2026

SPIN Processed News Frame: The Hype

Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning

Researchers introduce Feedback Manipulation Regularization (FMR), an algorithm-agnostic method that uses evaluative feedback to improve alignment in offline imitation learning, validated on adapted Safety Gymnasium environments with up to 98% reduction in misalignment.

Spin 75% Claim Present in Source AI Risk High
arXiv Artificial Intelligence

Jul 10, 2026