Research
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.

168,657 papers · 148 categories

Trend · papers per month

2875758621,149 · Jun 202019922001200920172026
48 results for biased offline data

The paper tackles bandit problems with biased offline data by using causal methods.

problem Improving bandit algorithms with biased offline data that includes confounding and selection biases.
method Formalizes the problem from a causal perspective, categorizes biases, and derives robust bounds for each arm.
result Causal bounds can guide the bandit agent to learn a nearly-optimal decision policy and consistently reduce asymptotic regret.

New method uses offline data to improve online bandit learning, even when distributions differ.

problem Improving online bandit learning with different offline and online distributions.
method MIN-UCB policy that adapts to offline data when informative, achieving tight regret bounds.
result MIN-UCB policy outperforms UCB policy with offline data and provides tight regret bounds.

This study simulates biases in classifiers to assess fairness.

problem Mitigating biases in predictive models to ensure fairness.
method Agent-based model (ABM) to generate synthetic datasets with controlled biases, applied to offline and online learning approaches.
result Demonstrates how biases in data affect classifier outcomes and how mitigations impact feature usage.

Machine learning models learn what we teach them to learn. Machine learning is at the heart of recommender systems. If a machine learning model is trained on biased data, the resulting recommender system may reflect the biases in its recommendations. Biases arise at different stages in a recommender system, from existi…

2019-05-10abs ↗pdf ↗

Paper tackles offline RL with limited target samples using domain adaptation.

problem Limited samples in target dataset degrade offline RL performance.
method Proposes a framework to balance target and source datasets with theoretical guarantees.
result Establishes performance bounds and optimal weight for offline RL.

This paper explores how IV methods can improve Q-function estimates in offline policy evaluation.

problem Confounding in estimating Q-function using reinforcement learning.
method Integrates IV techniques into offline policy evaluation (OPE) to improve Q-function estimates.
result State-of-the-art OPE methods are closely matched in performance by some IV methods.

Method uses pseudo-samples to improve RCT data in ride-hailing pricing studies.

problem Small and biased RCT data leads to significant bias when generalizing to broader user base.
method Pseudo-sample matching to expand and match RCT data with observational data.
result 0.41% improvement in profit through pseudo-sample matching.

Algorithm learns from offline data to improve performance in target environment.

problem Learning from offline data in a target environment with unknown shifts.
method Adaptive algorithm that uses offline data to improve performance when informative.
result Algorithm provably improves performance over purely online learning when offline data are informative.

Q-Distribution Guided Q-Learning corrects overestimation of uncertain OOD actions in offline RL.

problem Overestimation of Q-values for out-of-distribution actions in offline reinforcement learning.
method QDQ applies a pessimistic adjustment to Q-values in uncertain OOD regions based on a consistency model.
result QDQ improves performance on the D4RL benchmark and achieves significant improvements across many tasks.

Data driven soft sensor design has recently gained immense popularity, due to advances in sensory devices, and a growing interest in data mining. While partial least squares (PLS) is traditionally used in the process literature for designing soft sensors, the statistical literature has focused on sparse learners, such …

2019-04-24abs ↗pdf ↗

A3RL combines online and offline RL with active sampling to improve policy learning.

problem Combining online and offline RL for sample efficiency and robustness.
method A3RL uses a confidence-aware Active Advantage Aligned (A3) sampling strategy to prioritize data from both online and offline sources.
result A3RL outperforms competing online RL techniques that use offline data.

Algorithm balances online and offline data for linear bandits.

problem Online learning with an offline dataset in linear bandits.
method Proposes a linear bandit algorithm that uses offline data early and increasingly favors exploration as the horizon grows.
result Establishes regret bounds showing competitive performance with both purely online and offline solutions.

New insights on offline RL with state aggregation and trajectory data.

problem Understanding sample complexity in offline policy evaluation.
method Analyzing concentrability coefficient in aggregated Markov Transition Model.
result Sample complexity depends on concentrability coefficient in aggregated model.

Anchor-TS uses median anchoring to improve online decision-making from offline data with distribution shift.

problem Improving online decision-making from offline data with distribution shift.
method Sample-Mean Anchored Thompson Sampling (Anchor-TS) with median anchoring.
result Anchor-TS safely leverages offline data to accelerate online learning and reduces regret.

Hybrid RL algorithm combines offline and online data for robust and efficient policy learning.

problem Combining robust on-policy methods with efficient offline data for hybrid RL.
method Integrates off-policy training on offline data into on-policy NPG framework.
result Achieves state-of-the-art theoretical guarantees and maintains on-policy NPG guarantees.

Survey of offline RL theory and practical algorithm design challenges.

problem Optimizing return from fixed agent trajectories without additional interactions.
method Theoretical insights and practical algorithm design.
result Conditions for practical offline RL algorithms and their limitations.

The paper studies OPE with missing data, showing bias under nonignorable missingness and proposing a solution.

problem Estimating value of a target policy from logged data with missingness.
method Investigates OPE with monotone missingness, proposes an IPW value estimator, and conducts statistical inference.
result Value estimates remain unbiased under ignorable missingness but can be biased under nonignorable missingness.

Paper proposes a hybrid RL algorithm that combines offline and online data without needing reward info.

problem How to efficiently use online data to improve RL policies using only offline data.
method A three-stage hybrid RL algorithm that uses reward-agnostic exploration and model-based offline RL.
result The hybrid RL algorithm outperforms both pure offline and pure online RL in sample complexity.

This work bridges offline RL and DRL to address distributional shift.

problem Distributional shift in offline RL due to difference in state-action visitation distributions.
method Proposes offline RL algorithms using DRL framework, characterizes sample complexity under single policy concentrability.
result Demonstrates superior performance of proposed algorithms through simulations.

A new offline RL framework unifies imitation learning and vanilla offline RL.

problem Learning from expert datasets without active data collection.
method A new offline RL framework that interpolates between imitation learning and vanilla offline RL, using a weak concentrability coefficient and a lower confidence bound algorithm.
result LCB algorithm achieves a faster rate of 1/N1/N for nearly-expert datasets, and is adaptively optimal for the entire data composition range.

Paper establishes baselines for offline RL from visual observations.

problem Challenges in offline reinforcement learning from visual observations with continuous action spaces.
method Simple baselines and benchmarking tasks for offline RL from visual observations.
result Simple modifications to existing online RL algorithms outperform existing offline RL methods.

Study minimax-optimal rates for offline decision-making with function approximation.

problem Statistical complexity of offline decision-making with function approximation.
method Near minimax-optimal rates for stochastic contextual bandits and Markov decision processes, using pseudo-dimension and behavior policy.
result Established performance limits and new characterization of behavior policy.

Bayesian optimization for long-term outcomes using fast and slow experiments.

problem Optimizing long-term system effects with short-term misleading results.
method Combining fast and slow experiments for Bayesian optimization.
result Sequential optimization over large action spaces in a short time.

This study tackles offline RL with perturbed data sources, deriving a lower bound and proposing an optimal algorithm.

problem Understanding offline RL with multiple perturbed data sources.
method Derives an information-theoretic lower bound, proposes HetPEVI algorithm considering sample and source uncertainties.
result HetPEVI is optimal up to a polynomial factor of the horizon length and can solve offline RL tasks.

A simple approach to offline RL without additional complexity.

problem Learning from a fixed dataset of actions with value estimation errors.
method Adding a behavior cloning term to the policy update of an online RL algorithm and normalizing the data.
result Matches the performance of state-of-the-art offline RL algorithms with minimal changes.

Offline RL with pre-trained features amplifies errors even under mild shifts.

problem Sample-efficient offline RL with pre-trained features under mild distribution shift.
method Empirical study of offline RL with pre-trained neural representations.
result Substantial error amplification occurs even with pre-trained features, requiring stronger conditions for successful offline RL.

ORIL learns a reward function from unlabeled data to improve robot learning.

problem Leveraging unlabeled data for robot learning.
method ORIL learns a reward function from demonstrator and unlabeled trajectories, annotates data, and trains an agent via offline reinforcement learning.
result ORIL consistently outperforms BC agents on various robotic tasks.

Adobe research tackles strategic recommendations using reinforcement learning.

problem Optimizing user interactions for long-term objectives in various use-cases.
method Reinforcement learning applied to modeling user behavior and decision-making.
result Practical solutions implemented for various use-cases, addressing fundamental challenges.

New ranking algorithms improve online content delivery by learning from click data.

problem Bias in ranking systems due to production system biases.
method Proposed novel extensions of LinUCB and Linear Thompson Sampling algorithms to handle position-based click model.
result Validated the proposed algorithms through offline and online experiments.

BOMS enhances offline MBRL by improving model selection with Bayesian optimization.

problem Inaccurate model selection in offline MBRL due to distribution shift.
method Proposes BOMS, an active model selection framework using Bayesian optimization.
result Improves model selection with only a small amount of online interaction.