Batched Neural Bandits reduces policy updates in sequential decision-making.
problem Sequential decision-making with batched policy changes.
method BatchNeuralUCB algorithm combining neural networks and optimism.
result Achieves similar regret as fully sequential version with fewer policy updates.
Batch Thompson Sampling reduces exploration-exploitation trade-off in online decision making.
problem Balancing exploration and exploitation in online decision making.
method Introducing a batch Thompson Sampling framework for stochastic multi-arm bandit and linear contextual bandit problems.
result Achieves asymptotic regret bound with O ( log T ) O(\log T) O ( log T ) batch queries, significantly reducing interactions. New algorithms for batch decision-making with high-dimensional user data.
problem Maximizing treatment efficacy in groups of users.
method Teamwork LASSO Bandit algorithm, switching between teamwork and selfish stages.
result Upper bound on expected cumulative regret for the proposed algorithm.
Study batch learning in linear bandits with context, achieving near-optimal performance.
problem Sequential batch learning in linear contextual bandits with finite actions.
method Established regret bounds and provided algorithms for two settings: arbitrary contexts and i.i.d. contexts.
result Regret upper bound nearly matches lower bound, showing polynomial and logarithmic batch requirements.
The paper tackles batch policy learning in Markov Decision Processes, focusing on average reward maximization.
problem Maximizing long-term average reward in Markov Decision Processes with batch learning.
method Doubly robust estimator for average reward, optimization algorithm for optimal policy, finite-sample regret guarantee.
result The proposed method achieves semiparametric efficiency and provides a finite-sample regret guarantee.
Novel algorithm reduces feature inclusion in online decision-making.
problem Optimizing decision-making for personalized user experiences with fairness.
method Online Batched Sequential Inclusion (OBSI) algorithm for sequential feature inclusion.
result OBSI outperforms other algorithms in terms of regret, relevance of features, and compute.
Proposes a new semi-parametric framework for batched bandits with covariates.
problem Sequential decision-making with batched feedback and contextual information.
method Batched single-Index Dynamic binning and Successive arm elimination (BIDS) using single-index regression.
result Achieves minimax-optimal rates for nonparametric batched bandits.
New algorithm improves knowledge transfer in dynamic decision-making.
problem Utilizing data from existing ventures to improve decision-making in new ventures.
method Proposes Transferred Fitted Q Q Q -Iteration algorithm for estimating optimal action-state function Q ∗ Q^* Q ∗ . result Significantly improved final learning error of Q ∗ Q^* Q ∗ function. BaNk-UCB tackles batched nonparametric bandits with k-NN regression and UCB.
problem Sequential decision-making with limited online feedback in domains like medicine and marketing.
method Combines k-NN regression with UCB principle for fully nonparametric, adaptive, and simple implementation.
result Near-optimal regret guarantees under Lipschitz smoothness and margin assumptions, with minimax-optimal rates.
The paper proposes a method to explain expert decisions by modeling preferences with 'what if' outcomes.
problem Interpreting and auditing decision-making policies in institutions.
method Integrating counterfactual reasoning into batch inverse reinforcement learning.
result The method effectively recovers accurate and interpretable descriptions of expert behavior.
A new method improves active learning for large batch sizes.
problem Challenges in scaling Bayesian active learning to large batch sizes.
method Derives Partial Batch Label Sampling (ParBaLS) for EPIG algorithm.
result ParBaLS EPIG outperforms top- B B B selection and BatchBALD. Paper proposes a new decision strategy for open set recognition.
problem Existing OSR methods are limited in recognizing unknown classes and setting decision thresholds.
method Introduces a collective decision-based OSR framework (CD-OSR) using Hierarchical Dirichlet process (HDP).
result CD-OSR can simultaneously implement open set recognition and new class discovery.
This paper unifies three regularization methods in batch reinforcement learning.
problem Learning overly-complex models in batch reinforcement learning.
method Unified weighted average transition matrix framework for three regularization methods.
result Empirical evaluation confirms intuitions about regularization methods' performance.
New batched Langevin Thompson Sampling reduces communication costs for sequential decision making.
problem Efficiently learning unknown reward distributions and transition dynamics in batched settings.
method Langevin Thompson Sampling with logarithmic communication costs.
result Order-optimal regret guarantees for stochastic MABs and RL.
Batch normalization improves deep networks by aligning their decision boundaries with data.
problem Improving the performance and generalization of deep networks.
method Theoretical analysis of batch normalization as a function approximation technique for continuous piecewise affine splines.
result Batch normalization adapts the geometry of a deep network's partition to match the data, improving learning and generalization.
A new method for risk-averse decision-making in Markov processes with improved regret bounds.
problem Risk-averse decision-making in Markov processes.
method Introduces mini-batch measures and multipattern risk-averse problems in a feature-based Q Q Q -learning method. result Proves a high-probability regret bound of O ( H 2 N H K ) \mathcal{O}\big(H^2 N^H \sqrt{ K}\big) O ( H 2 N H K ) for the Q Q Q -learning method. Stochastic Gradient Trees learn decision trees incrementally.
problem Learning decision trees using stochastic gradient information.
method Incremental learning setting, soft splits not used, new tree not constructed per update.
result Performs similarly to standard incremental classification trees, outperforms state of the art incremental regression trees, comparable to batch multi-instance learning methods.
Online learning framework for inverse optimization improves decision-making in noisy data.
problem Real-time decision-making with noisy data and limited historical information.
method Developed an online learning algorithm with implicit update rule for noisy data.
result Algorithm converges at O ( 1 / T ) \mathcal{O}(1/\sqrt{T}) O ( 1/ T ) rate and is statistically consistent. Active learning performance degrades with larger batch sizes, but can be mitigated with smaller window sizes.
problem Impact of batch size on stopping active learning for text classification.
method Analyzed the impact of batch size on a stopping method for active learning in text classification, finding that larger batch sizes degrade performance and that using smaller window sizes mitigates this effect.
result Mitigating batch size degradation in active learning for text classification can be achieved by adjusting the window size parameter.
Ensembles of randomized decision trees, usually referred to as random forests, are widely used for classification and regression tasks in machine learning and statistics. Random forests achieve competitive predictive performance and are computationally efficient to train and test, making them excellent candidates for r…
Optimizes harvesting in biopharmaceutical fermentation with limited data.
problem High variability in fermentation outputs due to model risk with small data.
method Stochastic model, Bayesian approach, Markov decision process.
result Improves fermentation output and reduces variability.
Study dynamic batch learning in high-dimensional sparse linear bandits.
problem Dynamic batch learning in high-dimensional sparse linear contextual bandits under batch constraints.
method Characterized fundamental learning limits via regret lower bound and provided matching upper bound.
result Prescribed an optimal scheme for dynamic batch learning in high-dimensional sparse linear contextual bandits.
We study the dynamics of a version of the batch minority game, with random external information and with different types of inhomogeneous decision noise (additive and multiplicative), using generating functional techniques à la De Dominicis. The control parameters in this model are the ratio α = p / N α=p/N α = p / N of the number p p p o…
Paper develops efficient nonmyopic active search methods for drug and materials discovery.
problem Efficiently identifying many members of a class in high-throughput screening.
method Bayesian decision framework, nonmyopic approximations, efficient computation.
result Proposed policy outperforms sequential and batch settings in drug and materials discovery.
BOE reformulates BO as a classifier for scalable batch optimisation.
problem Scalable batch optimisation of expensive functions.
method Reformulates BO as density-ratio estimation, removing need for explicit function prior.
result Theoretical guarantees and improved uncertainty estimates for batch optimisation.
New insights explain speedup saturation in distributed learning with large batches and delays.
problem Understanding and optimizing speedup in distributed learning with large batches and delays.
method Theoretical analysis of strongly convex, convex, and non-convex settings, considering data sparsity.
result Identification of a data-dependent parameter explaining speedup saturation in both batch size and gradient staleness.
μ-cuDNN accelerates deep learning frameworks with micro-batching.
problem Slow performance and memory constraints in GPU kernels.
method Divides layers' mini-batch computation into micro-batches using Dynamic Programming and Integer Linear Programming.
result Achieved speedups of 1.63x for AlexNet and 1.21x for ResNet-18 on P100-SXM2 GPU.
Extremely Fast Decision Tree improves accuracy on large datasets.
problem Improving accuracy on large classification datasets.
method Hoeffding Anytime Tree, a modified version of Hoeffding Tree.
result Extremely Fast Decision Tree achieves superior prequential accuracy on most UCI datasets.
New batch RL method avoids overly optimistic policies.
problem Challenges in applying RL to large domains with limited data.
method Modified Bellman optimality and evaluation back-up for conservative updates.
result Can find approximately best policies within explored state-action space.
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.
BINOCULARS improves experimental design by balancing exploration and exploitation.
problem Efficiently balancing exploration and exploitation in sequential experiments.
method BINOCULARS computes a batch of experiments, then selects a single point to evaluate, avoiding myopic approaches.
result BINOCULARS significantly outperforms myopic alternatives in real-world scenarios.
Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD): the variance in predicted probability of the correct class across iterations of …
This paper tackles batch Bayesian optimal experimental design by using Wasserstein gradient flows.
problem The challenge of optimising high-dimensional, strongly non-convex expected information gain in batch settings.
method Probabilistic lifting to the space of probability measures, entropic regularisation, Wasserstein gradient flow, and particle-based algorithms.
result The proposed approach can be used directly as a randomised batch-design policy or as a computational relaxation.
Efficient RL algorithms for linear function approximation with limited adaptivity constraints.
problem Limited adaptivity in reinforcement learning with linear function approximation.
method Proposed two efficient online RL algorithms for episodic linear Markov decision processes under batch learning and rare policy switch models.
result Achieved efficient regret bounds for both batch learning and rare policy switch models, with substantial reduction in adaptivity.
Improved deep probabilistic time series forecasting by learning error autocorrelation.
problem Simplification of time-independent error process and lack of serial correlation in existing models.
method Proposes a training method that incorporates error autocorrelation to enhance probabilistic forecasting accuracy.
result Improves predictive accuracy and uncertainty quantification across multiple datasets.
A new algorithm learns policies from batch data in hierarchical RL.
problem Learning policies from fixed batches of data without full exploration.
method Modeling RL as a two-player game with a leader-follower structure, proposing StackelbergLearner.
result StackelbergLearner achieves competitive performance in batch RL and real-world datasets.
Optimized decision trees for reinforcement learning, improving sample complexity and interpretability.
problem Updating decision trees online in reinforcement learning.
method Gradient update over differentiable decision trees, including theoretical justification and empirical validation.
result Our approach outperforms neural networks in sample complexity and achieves higher rewards online.
We improve neural network explainability by bypassing batch normalization.
problem Lack of transparency in neural networks.
method Layer-wise Relevance Propagation with a method to include normalization layers.
result Heatmaps are more accurate for convolutional layers with our method.
A new reinforcement learning method for medical decisions with limited data.
problem Learning high-performing policies from partially observed data in healthcare.
method Optimization objective that combines policy and generative model quality, suitable for batch off-policy settings.
result Demonstrated improved performance on synthetic and medical decision-making problems.
DETC algorithm achieves asymptotic optimality in multi-armed bandit problems.
problem Multi-armed bandit problem with subgaussian rewards.
method DETC algorithm with two exploration and exploitation phases.
result DETC achieves asymptotically optimal regret bound.
Study batch reinforcement learning methods for personalized medical treatments.
problem Batch reinforcement learning for personalized medical treatments.
method Direct policy learning and model-based learning approaches.
result Model-based learning is impossible with finite model classes but feasible with relaxed conditions.
Meta-algorithm for efficient reinforcement learning from human preferences.
problem Learning from human preference comparisons in Markov decision processes.
method Randomized exploration and experimental design for batch comparison queries.
result Meta-algorithm achieves both regret and last-iterate guarantees with minimal preference queries.
Framework learns linear programs from optimal decisions.
problem Learning linear programs from optimal decisions is challenging.
method Gradient-based framework for learning linear programs from optimal decisions.
result Successfully learns linear programs and multi-commodity flow instances.
STEEL tackles batch RL with singularity, improving policy optimization.
problem Existing RL methods assume absolutely continuous data, but STEEL handles non-overlapping regions.
method Proposes STEEL algorithm using maximum mean discrepancy and distributionally robust optimization.
result First finite-sample regret guarantee for batch RL with singularity.
Study mini-batch SGD noise and its limits, proving complexity guarantees.
problem Analyzing the noise in mini-batch SGD and its impact on optimization.
method Examined the conditional covariance and diffusion limits of SGD under different sampling designs.
result Proved mean-square upper bounds and Fisher van Trees lower bounds for SGD, linking them to effective dimension and condition number.
The paper tackles robust policy learning in MDPs using statistical methods.
problem Offline data-driven sequential decision making in MDPs.
method Evaluates policies using average rewards centered at policy-induced stationary distributions. Developed a statistically efficient method for estimating robust optimal policies.
result Established a rate-optimal regret bound up to a logarithmic factor.
PAC best arm identification with a deadline, improving efficiency over sequential methods.
problem Identifying an optimal arm under a fixed time constraint.
method Elastic Batch Racing (EBR) algorithm for ( ε , δ ) (ε, δ) ( ε , δ ) -PAC best arm identification under a deadline. result EBR is optimal with respect to two hardness results and outperforms sequential methods.
Deep learning uses ROC cost functions to improve virtual screening accuracy.
problem Challenges in training deep learning models for virtual screening, especially class imbalance and lack of ground truth labels.
method Proposes using ROC cost functions to optimize deep learning models for virtual screening, introduces new training schemes and cost functions.
result Demonstrates improved performance of ROC-based approaches on PubChem datasets.