On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “Inverse-Gap-Weighting”

Interaction-Grounded Learning for Contextual Markov Decision Processes with Personalized Feedbackcs.LG

Efficient algorithm for learning from indirect feedback in complex decision-making scenarios.

problem Learning from indirect feedback in realistic scenarios with personalized mechanisms.

method IGW algorithm for policy optimization, extending reward-estimator construction from single-step to multi-step.

result Achieves sublinear regret guarantee for contextual episodic MDPs with personalized feedback.

Markov Decision Processes Personalized Feedback Inverse-Gap-Weighting Efficient Algorithms Sublinear Regret

2026-02-09abs ↗pdf ↗

Provably Efficient Interactive-Grounded Learning with Personalized Rewardcs.LG

New algorithms improve efficiency in learning from personalized rewards.

problem Learning from personalized rewards in recommendation systems.

method Developed provably efficient algorithms with sublinear regret for context-dependent feedback.

result Introduced a Lipschitz reward estimator that improves generalization performance.

Interactive-Grounded Learning Personalized Rewards Sublinear Regret Lipschitz Estimator Inverse-Gap Weighting

2024-05-31abs ↗pdf ↗

Harnessing the Power of Federated Learning in Federated Contextual Banditsstat.ML

This work bridges federated learning and contextual bandits, enhancing FL's utility.

problem Limited use of federated learning in contextual bandits despite its potential.

method Proposes FedIGW, a novel federated contextual bandits design that leverages regression-based algorithms and integrates various FL components.

result FedIGW better harnesses FL innovations and provides flexible, modular, and seamless integration of FL elements.

federated learning contextual bandits federated contextual bandits inverse gap weighting flexibility

2023-12-26abs ↗pdf ↗

Conservative Contextual Bandits: Beyond Linear Representationscs.LG

Develops algorithms for CCBs with non-linear costs, improving safety and performance.

problem Safety constraints in sequential decision making with non-linear arm costs.

method Innovative algorithms using Inverse Gap Weighting (IGW) and online regression oracle.

result Sub-linear regret bounds for C-SquareCB and first-order regret for C-FastCB.

Conservative Contextual Bandits Safety Constraints Non-linear Costs UCB Algorithms Inverse Gap Weighting

2024-12-09abs ↗pdf ↗

Top-

k

eXtreme Contextual Bandits with Arm Hierarchystat.ML

A new algorithm for selecting top-k arms in extreme contextual bandits with improved efficiency.

problem Selecting top-k arms from a large set with contextual information and limited rewards.

method Proposes an algorithm for both non-extreme and extreme settings, using Inverse Gap Weighting and arm hierarchy models.

result Achieves improved regret guarantees for extreme settings with significant computational and statistical efficiency.

contextual bandits top-k selection extreme settings arm hierarchy regret analysis

2021-02-15abs ↗pdf ↗