New methods improve offline A/B testing for recommender systems to avoid financial losses.
problem Detecting poor policies in recommender systems without losing money.
method Proposed two variants of counterfactual estimates to reduce bias and variance.
result Proposed methods correlate with business metrics in real-world conditions.
New algorithms improve FDR control in sequential hypothesis testing.
problem Balancing offline and online approaches for FDR control.
method Introducing Batch_{BH} and Batch_{St-BH} algorithms.
result Interpolates between offline and online methods, improving FDR control.
Paper tackles offline meta-reinforcement learning with a new algorithm.
problem Performing reinforcement learning on limited data from a new task.
method Meta-Actor Critic with Advantage Weighting (MACAW) algorithm.
result Achieves notable gains over prior methods on offline meta-RL benchmarks.
Combines offline causal inference and online bandit learning for better decision-making.
problem Making adaptive decisions using both logged and streaming data to avoid user harm.
method Unified offline causal inference and online learning algorithms, deriving bounds on decision accuracy.
result First upper regret bound for forest-based online bandit algorithms.
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.
One-Class Classification (OCC) has been prime concern for researchers and effectively employed in various disciplines. But, traditional methods based one-class classifiers are very time consuming due to its iterative process and various parameters tuning. In this paper, we present six OCC methods based on extreme learn…
Paper presents a deep reinforcement learning algorithm for online trading without offline training.
problem Developing a fully online trading algorithm without offline training.
method Double Deep Q-learning with Fast Learning Networks, defining terminal states for money conservation. result The algorithm outperforms random action trading and captures different market trends.
The paper develops online methods to control familywise error rate in growing hypothesis testing sequences.
problem Controlling familywise error rate in a growing sequence of hypotheses over time.
method Unified algorithmic concepts for offline and online FWER control, including new adaptive online algorithms.
result Substantial gains in power demonstrated and formally proved in a Gaussian sequence model.
New exact tests detect changepoints in binary and count data, especially when normal approximations fail.
problem Detecting changepoints in multichannel binary and count data.
method Exact tests combining two-sample conditional tests with multiplicity correction.
result Exact tests are much more powerful than asymptotic tests in various settings.
ESRL uses uncertainty quantification to learn safe, optimal policies in offline RL.
problem Challenges in interpreting and measuring uncertainty of learned policies in offline RL.
method Expert-Supervised Reinforcement Learning (ESRL) framework that uses hypothesis testing and posterior distributions.
result The framework can learn safe and optimal policies with theoretical guarantees and independent sample efficiency.
HOFLON automates process start-ups and grade-changes using offline RL and online optimization.
problem Manual operation of start-ups and grade-changes by experts is declining, leaving plant owners without the necessary tacit know-how.
method HOFLON combines offline RL to learn a latent manifold and long-horizon Q-critic, and online optimization to maximize Q-critic while penalizing deviations and excessive variable changes.
result HOFLON outperforms standard offline RL in industrial case studies, delivering better cumulative rewards than historical data.
CausalCOMRL improves RL task representations by integrating causal relationships, enhancing generalizability.
problem Spurious correlations in context-based offline meta-reinforcement learning.
method CausalCOMRL integrates causal representation learning to uncover and incorporate causal relationships among task components.
result CausalCOMRL achieves better performance on meta-reinforcement learning benchmarks.
New algorithm uses imperfect advice to improve online bipartite matching performance.
problem Online bipartite matching with imperfect advice.
method Designing an algorithm that uses external advice to improve performance between advice-free methods and optimal ratio.
result Algorithm achieves competitive ratio interpolating between advice-free methods and optimal ratio of 1.
Paper addresses inconsistency between offline and online LTR performance.
problem Inconsistency between offline and online LTR performance in E-commerce.
method Proposes an evaluator-generator framework to maximize evaluator score using reinforcement learning.
result Significant improvement in Conversion Rate (CR) over existing models.
aLTT selects hyperparameters efficiently with statistical guarantees.
problem Statistical validity and efficiency in hyperparameter selection.
method Sequential data-dependent multiple hypothesis testing with early termination.
result Reduces testing rounds while maintaining statistical validity.
Novel optimization method detects change points in Gaussian data.
problem Detecting change points in univariate Gaussian data sequences.
method Continuous optimization for best subset selection (COMBSS) applied to a reformulated statistical inverse problem.
result Adaptation and evaluation of COMBSS for offline normal mean multiple change-point detection.
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.
Framework explains deep learning generalization by comparing real and ideal worlds.
problem Understanding why deep models generalize well in practice.
method Integrates real-world empirical loss with ideal population loss to decompose test error.
result The gap between real and ideal worlds is small in deep learning, suggesting robust optimization leads to good generalization.
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.
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.
SPQR improves Q-ensemble diversity in reinforcement learning.
problem Overestimation bias in Q-learning for complex tasks.
method Introduces SPQR for Q-ensemble independence regularization.
result SPQR outperforms baseline algorithms in online and offline RL benchmarks.
Post-detection analysis identifies responsible coordinates for multivariate change-points.
problem Identifying which coordinates in multivariate time series change after a detected change-point.
method Two-sample testing procedures with nonparametric tests for Type I error control.
result Strong performance of proposed post hoc statistical procedures.
Algorithm reduces online regret by leveraging offline data in linear bandits.
problem Online regret minimization in linear bandits with offline data.
method OOPE algorithm using extended D-optimal design.
result Substantial reduction in online regret compared to prior work.
Risk monitoring detects when TTA models degrade at test time.
problem Detecting when TTA models degrade at test time.
method Extended risk monitoring tools based on sequential testing with confidence sequences.
result Demonstrated effectiveness of TTA monitoring framework across various datasets and methods.
New method selects best offline RL policies from logged data.
problem Hyperparameter selection challenges offline RL.
method Offline hyperparameter selection for RL algorithms.
result Reliable ranking and selection of policies across hyperparameters.
CAB estimator improves evaluation and learning performance in policy contexts.
problem Offline A/B-testing and off-policy learning using logged contextual bandit feedback.
method Continuous Adaptive Blending (CAB) estimator, subsuming most counterfactual estimators.
result CAB estimator is less biased and has less variance than other estimators.
Optimized RL algorithms perform well on offline datasets, outperforming fully trained agents.
problem Improving reinforcement learning performance on offline datasets.
method Random Ensemble Mixture (REM) algorithm for Q-learning, trained on DQN replay dataset.
result Offline REM outperforms strong RL baselines and fully trained DQN agent.
New method tackles safe reinforcement learning from offline data.
problem Learn optimal policies from fixed data while adhering to safety constraints.
method Combines offline RL with online optimization to minimize cumulative cost.
result Proves approximate optimality of the approach under certain conditions.
Model-X test detects conditional independence in streaming data.
problem Detecting conditional independence in data streams with arbitrary dependency.
method Sequential testing inspired by model-X and testing by betting.
result Significantly reduces type-I error rate and enhances data efficiency.
Proposes PEMI for online selective conformal prediction with asymmetric rules.
problem Challenges of handling asymmetric selection mechanisms in online selective conformal prediction.
method PEMI: permutation-based framework for selective conformal prediction with arbitrary asymmetric selection rules.
result Achieves exact selection-conditional coverage for any asymmetric selection mechanism and any prediction model.
Fine-tuning RL with offline data reduces online interactions.
problem Optimizing RL with limited online interactions and offline data.
method Developed algorithm extsc{FTPedel} for MDPs with linear structure.
result Optimally reduces the number of online interactions needed.
MOReL learns offline RL policies using pessimistic MDPs.
problem Offline RL's data efficiency and velocity.
method Two-step process: learn P-MDP and near-optimal policy in it.
result MOReL is minimax optimal and matches state-of-the-art results.
POIS optimizes policies using importance sampling bounds.
problem Optimizing policies in reinforcement learning with variance control.
method POIS algorithm for policy search, using importance sampling bounds and surrogate optimization.
result POIS achieves state-of-the-art performance on continuous control tasks.
Paper offers a fast convergence theory for offline decision making.
problem Offline decision making problems, including reinforcement learning and off-policy evaluation.
method Introduces a framework (DMOF) and algorithm (EDD) with a fast convergence guarantee.
result Demonstrates a fast convergence guarantee with a lower bound complement.
Study finds methods to learn multiple solutions from single task in offline RL.
problem Learning multiple solutions from a single task in offline RL.
method Proposed algorithms for offline RL.
result Empirical results show learning of multiple solutions in offline RL.
FOCUS improves offline RL by incorporating causal structure into world-models.
problem Learning effective policies from historical data without interaction.
method FOCUS proposes a practical algorithm that learns and leverages causal structure in offline RL.
result FOCUS outperforms plain model-based offline RL algorithms and other causal model-based RL algorithms.
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.
Novel RL algorithms learn from human interaction data without exploration.
problem Efficiently learning from off-policy data in reinforcement learning.
method Developed off-policy batch RL algorithms using KL-control and dropout-based uncertainty.
result Successfully learned multiple reward functions from human interaction data.
Framework reduces contextual bandit learning to offline regression with near-optimal regret.
problem Efficient learning with large action spaces and complex reward functions.
method Offline Estimation to Decisions (OE2D) algorithm that minimizes regret with near-optimal oracle calls.
result Near-optimal regret for contextual bandits with large action spaces and O(log(T)) offline oracle calls. 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.
RORL improves offline RL robustness with conservative smoothing.
problem Distribution shift and robustness issues in offline RL.
method RORL introduces regularization and conservative smoothing for robustness.
result RORL achieves state-of-the-art performance and robustness to adversarial perturbations.
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.
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.
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/N for nearly-expert datasets, and is adaptively optimal for the entire data composition range. 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.
Offline RL policies should adapt to unknown aspects of the environment.
problem Uncertainty in offline RL datasets leads to suboptimal policies.
method Adaptive policies that consider all transitions seen so far, solving an implicit POMDP.
result Optimal adaptive policies improve offline RL performance.
New algorithm for offline RL with linear approx in MDPs and MGs, nearly optimal.
problem Offline RL with linear function approximation in MDPs and MGs.
method Pessimism-based algorithm with uncertainty decomposition via reference function.
result Nearly minimax optimal performance in offline RL for MDPs and MGs.
Deep transfer learning from Persian handwriting improves offline signature verification.
problem Challenges in offline signature verification, especially with skilled forgeries and limited training data.
method Transfer learning approach from Persian handwriting to multi-language OSV, using Residual CNNs for feature learning and SVMs for verification.
result Significant improvement in Equal Error Rate (EER) on UT-Sig dataset (9.80% EER), surpassing state-of-the-art methods.