Meta-learners improve causal effect estimation in small samples.
problem Estimating causal effects using machine learning methods.
method Sample-splitting and cross-fitting to reduce overfitting bias.
result Meta-learners' performance depends on sample size and estimation procedure.
Bayesian neural networks show good correlation between out-of-sample performance and Bayesian evidence.
problem Improving the out-of-sample performance of Bayesian neural networks.
method Numerical sampling of Bayesian posterior, ensembling over architectures, analysis of evidence vs. model size.
result Good correlation between out-of-sample performance and Bayesian evidence; ensembling improves performance.
In biospectroscopy, suitably annotated and statistically independent samples (e. g. patients, batches, etc.) for classifier training and testing are scarce and costly. Learning curves show the model performance as function of the training sample size and can help to determine the sample size needed to train good classi…
Contrastive learning performance doesn't degrade with more negative samples.
problem Theoretical and empirical evidence of negative samples hurting performance in contrastive learning.
method Simple theoretical setting and empirical support on CIFAR-10 and CIFAR-100 datasets.
result Contrastive learning performance does not degrade with the number of negative samples.
Hierarchical GANs reduce anomaly detection costs.
problem Balancing anomaly detection accuracy and sampling costs.
method Hierarchical GANs for nonuniform sampling and buffer zones.
result Proposed GAN-based detector outperforms baseline in detection delay and average cost of error.
The paper tackles imbalance in production data by proposing sampling methods to improve model performance on underrepresented observations.
problem Imbalance in production data negatively impacts model predictive performance on underrepresented observations.
method Three sampling approaches are investigated to adjust for imbalance in training data and improve model performance.
result Fitting a model using sampled data yields a small reduction in overall predictive performance but a better performance on underrepresented observations.
Paper extends Chernoff sampling for active testing and parameter estimation, improving neural network and regression models.
problem Reducing sample complexity in hypothesis testing and model parameter estimation.
method Developed an extension of Chernoff sampling for active learning and parameter estimation.
result Non-asymptotic bounds for sample complexity and estimation error in active learning.
New sampling methods improve classifier performance estimation.
problem Efficiently selecting data points to estimate classifier performance.
method Introduced and compared Importance Sampling and Poisson Sampling.
result Poisson Sampling outperforms Importance Sampling.
In reinforcement learning, policy gradient algorithms optimize the policy directly and rely on sampling efficiently an environment. Nevertheless, while most sampling procedures are based on direct policy sampling, self-performance measures could be used to improve such sampling prior to each policy update. Following th…
Efficiently tests two distributions with few label queries.
problem Two-sample test with limited label information.
method Three-stage framework: classifier training, bimodal query, FR test.
result Significantly reduces Type II error compared to uniform querying.
Investments with best performance are not associated with best Sharpe ratios.
problem The relationship between performance and risk-adjusted return (Sharpe ratio) is counterintuitive for heavy-tailed distributions.
method Synthetic and real data analysis of returns distributions.
result The best-performing investments are not the best in terms of Sharpe ratio, and vice versa.
Validates policies using past observational data with guarantees about out-of-sample performance.
problem Evaluating decision policies using past data observed under a different policy.
method Sample-splitting method to draw inferences about the entire loss distribution with finite-sample coverage guarantees.
result Valid inferences about out-of-sample loss with finite-sample coverage guarantees, accounting for model misspecifications.
Develops robust MDPs for unknown disturbances with performance guarantees.
problem Unknown disturbance distribution in MDPs.
method Empirical distribution, sublevel set of distance function, weak convergence, concentration inequality.
result Robust optimal value function converges to true optimal value function with increasing sample sizes.
Gradient-guided nested sampling improves posterior inference efficiency.
problem Efficiently sampling from complex posterior distributions.
method Gradient-guided nested sampling combining differentiable programming, Hamiltonian slice sampling, clustering, mode separation, dynamic nested sampling, and parallelization.
result Significantly faster mode discovery and more accurate partition function estimates.
AES improves policy gradient performance by adaptively selecting experience.
problem High variance in gradient estimators from past trajectories.
method AES learns an adaptive sampling distribution to minimise gradient variance.
result AES leads to significantly improved performance in continuous control tasks.
GLASS Flows improves flow and diffusion model performance by optimizing sampling efficiency.
problem Efficiency bottleneck in sampling Markov transitions for flow and diffusion models.
method Introduces GLASS Flows, a new sampling paradigm that simulates a 'flow matching model within a flow matching model' to sample Markov transitions efficiently.
result Eliminates the trade-off between stochastic evolution and efficiency in large-scale text-to-image models.
Method estimates model performance on external samples from limited statistical characteristics.
problem Limited access to multiple datasets due to privacy and commercial restrictions.
method Search for weights that match external statistics and are closest to uniform, using model performance on weighted internal sample as an estimation.
result Estimated external performance is closer to actual performance than internal performance.
New framework analyzes why more negative samples improve self-supervised learning performance.
problem Inconsistency between theoretical degradation and empirical improvement of downstream supervised tasks with more negative samples.
method Coupon collector's problem framework to analyze self-supervised representation learning with more negative samples.
result Bound can implicitly incorporate supervised loss in self-supervised loss by increasing negative samples.
New causal models perform poorly when evaluated on biased training sets.
problem Sample selection bias affects the evaluation of causal models' prediction performance.
method Re-evaluated prediction performance of causal models on a genetic perturbation data set, proposing a less-biased evaluation set.
result Causal models have similar or worse performance when evaluated on a less-biased set compared to standard association-based estimators.
Improved Thompson Sampling outperforms existing Bayesian optimization methods.
problem Thompson Sampling's performance in Bayesian optimization is suboptimal compared to other methods.
method Developed Stagger Thompson Sampler (STS), which more precisely samples the optimal arm with less computation.
result STS outperforms TS, PSS, and other acquisition methods in various optimization tasks.
Predictive sampling improves on Thompson sampling for non-stationary bandit environments.
problem Thompson sampling fails in non-stationary bandit environments.
method Proposes predictive sampling, which deprioritizes actions based on information loss rate.
result Predictive sampling outperforms Thompson sampling in all tested non-stationary environments.
New algorithms for sampling in constrained domains without learning rates.
problem Sampling in constrained domains with fairness constraints and post-selection inference.
method Coin betting ideas from convex optimisation and a unifying framework for constrained sampling.
result Our algorithms achieve competitive performance without hyperparameter tuning.
New method improves deep learning by sampling worst-performing data.
problem Overfitting and poor generalization in deep learning.
method Distributional robust optimization to modify sample contributions.
result Faster convergence and higher accuracy in different scenarios.
WeakNAS uses a set of weaker predictors to find top architectures with fewer samples.
problem Finding the best neural architecture with heavy computation costs.
method Proposes a paradigm shift from fitting the whole architecture space to progressively fitting a search path through a set of weaker predictors.
result WeakNAS produces coarse-to-fine iteration to gradually refine the ranking of sampling space, requiring fewer samples to find top-performance architectures.
Improves MCMC performance with adaptive affine transformations.
problem Improving the performance of Markov Chain Monte Carlo samplers.
method Adaptive learning of bijective affine transformations during sampling.
result Adaptive affine transformations improve the quality of samples at low computational cost.
The combined algorithm selection and hyperparameter tuning (CASH) problem is characterized by large hierarchical hyperparameter spaces. Model-free hyperparameter tuning methods can explore such large spaces efficiently since they are highly parallelizable across multiple machines. When no prior knowledge or meta-data e…
Conventional approaches of sampling signals follow the celebrated theorem of Nyquist and Shannon. Compressive sampling, introduced by Donoho, Romberg and Tao, is a new paradigm that goes against the conventional methods in data acquisition and provides a way of recovering signals using fewer samples than the traditiona…
RISA improves VFL by using imputed samples with low uncertainty.
problem Limited overlapping samples constrain VFL performance.
method Imputing non-overlapping samples and using evidence theory to select reliable imputed samples.
result Significant performance gains achieved, especially with limited overlapping samples.
Paper improves Thompson Sampling for linear contextual bandits.
problem Empirical Thompson Sampling does not achieve optimal regret bounds.
method Develops a novel estimator with adaptive data augmentation and coupling.
result Achieves nearly minimax optimal performance.
Paper presents a new way to analyze machine learning generalization without probabilistic assumptions.
problem Traditional generalization analysis assumes i.i.d. data, which is often unverifiable.
method Uses sensitivity analysis of optimization problems to derive deterministic generalization bounds.
result Obtains generalization bounds that relate in-sample and out-of-sample evaluations through an error term quantifying data similarity.
Thompson sampling provides a solution to bandit problems in which new observations are allocated to arms with the posterior probability that an arm is optimal. While sometimes easy to implement and asymptotically optimal, Thompson sampling can be computationally demanding in large scale bandit problems, and its perform…
A new CVaR test reduces group performance disparity detection complexity.
problem Detecting performance disparities across multiple sensitive groups in ML models.
method Conditional Value-at-Risk (CVaR) testing to reduce sample complexity.
result Sample complexity reduced exponentially to be at most the square root of the number of groups.
We aim to develop off-policy DRL algorithms that not only exceed state-of-the-art performance but are also simple and minimalistic. For standard continuous control benchmarks, Soft Actor-Critic (SAC), which employs entropy maximization, currently provides state-of-the-art performance. We first demonstrate that the entr…
The paper proves concentration inequalities for two-sample rank processes and applies them to ranking performance criteria.
problem Measuring the performance of ranking statistics between two populations.
method Proves concentration inequalities for two-sample rank processes indexed by VC classes of scoring functions.
result Generalization capacity of empirical maximizers of ranking performance criteria is investigated.
MRCs minimize worst-case expected 0-1 loss and provide performance guarantees.
problem Minimizing expected 0-1 loss in classification.
method Minimizes worst-case expected 0-1 loss over uncertainty sets defined by linear constraints.
result Achieves efficient learning and generalization with performance guarantees.
Bagging, a powerful ensemble method from machine learning, improves the performance of unstable predictors. Although the power of Bagging has been shown mostly in classification problems, we demonstrate the success of employing Bagging in sparse regression over the baseline method (L1 minimization). The framework emplo…
Improves test set performance and reduces out-of-sample disappointment for unstable models.
problem Ensuring strong test set performance via cross-validation for unstable models.
method Nested k-fold cross-validation with hyperparameter selection based on a weighted sum of cross-validation metric and model stability measure.
result Improves out-of-sample MSE for sparse ridge regression and CART by 4% and 2% respectively, compared to k-fold cross-validation.
Monte Carlo (MC) sampling algorithms are an extremely widely-used technique to estimate expectations of functions f(x), especially in high dimensions. Control variates are a very powerful technique to reduce the error of such estimates, but in their conventional form rely on having an accurate approximation of f, a pri…
Differentially private weighted sampling improves privacy while maintaining utility.
problem Ensuring privacy in datasets with key-value pairs while preserving analytical utility.
method Private Weighted Sampling (PWS) that ensures element-level differential privacy.
result Significant performance gains in key reporting and estimation accuracy compared to prior methods.
Study shows sample noise impacts active learning performance.
problem Impact of sample noise on active learning performance.
method Proposed Incremental Weighted K-Means for noisy samples.
result Robust sampler improves synthetic tasks but only marginally in real-life.
We unify slice sampling and Hamiltonian Monte Carlo (HMC) sampling, demonstrating their connection via the Hamiltonian-Jacobi equation from Hamiltonian mechanics. This insight enables extension of HMC and slice sampling to a broader family of samplers, called Monomial Gamma Samplers (MGS). We provide a theoretical anal…
Proposes a Siamese NN for algorithm selection focusing on alike performing instances.
problem Lack of effective meta-features for algorithm selection via meta-learning.
method Siamese Neural Network architecture with 'Algorithm-Performance Personas' concept.
result Proposed metric outperforms standard performance metrics in training sample selection.
FedCVT improves VFL models with limited aligned samples.
problem Limited aligned samples in VFL.
method Cross-view training to estimate missing features and predict pseudo-labels.
result FedCVT significantly outperforms vanilla VFL.
Median-of-means sampling outperforms mean-of-means for large sample sizes in numerical integration.
problem Improving numerical integration accuracy in high dimensions.
method Median-of-means sampling compared to mean-of-means using RQMC methods.
result Median-of-means sampling is superior for large sample sizes, while mean-of-means is better for smaller sample sizes.
GGFPS improves model performance by sampling molecules more efficiently.
problem Improving model performance and reducing data costs in chemistry problems.
method Gradient-Guided Furthest Point Sampling (GGFPS) that leverages molecular force norms.
result GGFPS leads to superior data efficiency and model robustness compared to other sampling methods.
New algorithm reduces sample complexity for Top Two method.
problem Fixed-confidence best arm identification for Top Two methods.
method UCB-based Top Two algorithm for non-asymptotic analysis.
result First non-asymptotic upper bound on expected sample complexity.
Leverage score sampling provides an appealing way to perform approximate computations for large matrices. Indeed, it allows to derive faithful approximations with a complexity adapted to the problem at hand. Yet, performing leverage scores sampling is a challenge in its own right requiring further approximations. In th…
Learn2Evaluate uses learning curves to estimate high-dimensional prediction performance.
problem Estimating test performance in high-dimensional data settings is challenging.
method Learn2Evaluate uses learning curves to estimate test performance at the total sample size.
result Learn2Evaluate provides a lower confidence bound for performance estimation.