Flexible estimator synthesizes noisy experiments and covariates for optimal effect estimation.
problem Simultaneous analysis of many noisy experiments with rich covariate information.
method Plug-in empirical Bayes estimator that synthesizes noisy experimental results and covariates.
result Within a constant factor of minimax for a simple data-generating model, and robust convergence guarantees hold under generality.
Synthetic experiments are crucial for assessing causal machine learning methods.
problem Current empirical evaluations of causal machine learning methods are insufficient and unreliable.
method Propose principles for conducting rigorous empirical analyses with synthetic data.
result Rigorous synthetic experiments are essential for building trust in causal machine learning methods.
Study finds real-world datasets contain natural experiments that can improve model performance.
problem Detecting natural experiments in real-world datasets for causal inference.
method Synthetic graph simulation and feature selection based on causal links.
result Real-world datasets contain natural experiments that can be exploited for improved model performance.
MushroomRL simplifies RL experiments for researchers.
problem Complexity in implementing and testing RL experiments.
method Provides a comprehensive and flexible framework to minimize effort.
result Significantly benefits RL researchers in empirical analysis.
New method uses predictions to infer causal effects without labeled data.
problem Data labeling costs limit causal inference experiments.
method Prediction-Powered Causal Inferences (PPCI) using conditional calibration and transfer constraints.
result Valid causal inference achieved on experiments with no human annotations.
Efficient classifier error estimation without re-training.
problem Estimating classifier error without re-training.
method Generalized resubstitution based on empirical measures.
result Consistent and asymptotically unbiased error estimation.
ReaPER improves learning efficiency by prioritizing reliable experiences.
problem Inefficient sampling of past experiences in reinforcement learning.
method Introducing a novel measure of reliability to prioritize experiences in PER.
result ReaPER outperforms PER in various environments, including Atari-10.
New algorithm optimizes unimodal bandits using empirical divergence.
problem Optimizing decisions in multi-armed bandit problems with unimodal distributions.
method Indexed Minimum Empirical Divergence (IMED) adapted for unimodal structure.
result IMED-UB algorithm optimally exploits unimodal structure.
Bayesian Deep Learning experiments often use weak baselines, leading to misleading conclusions.
problem Misleading conclusions in Bayesian Deep Learning due to weak baselines in experiments.
method Used a fixed number of iterations for baselines and compared them with models trained to convergence.
result Monte Carlo dropout baseline outperforms or performs competitively with superior methods.
We develop an empirical behavioural order-driven (EBOD) model, which consists of an order placement process and an order cancellation process. Price limit rules are introduced in the definition of relative price. The order placement process is determined by several empirical regularities: the long memory in order direc…
This work proves L 2 L_2 L 2 -regularized ERM controls smCE without post-hoc correction.
problem Calibration of predicted probabilities in machine learning models.
method Canonical L 2 L_2 L 2 -regularized empirical risk minimization. result Theoretical proof that smCE is controlled by ERM without post-hoc correction.
This paper studies the partial estimation of Gaussian graphical models from high-dimensional empirical observations. We derive a convex formulation for this problem using ℓ 1 \ell_1 ℓ 1 -regularized maximum-likelihood estimation, which can be solved via a block coordinate descent algorithm. Statistical estimation performance …
We explore the possibility of using machine learning to identify interesting mathematical structures by using certain quantities that serve as fingerprints. In particular, we extract features from integer sequences using two empirical laws: Benford's law and Taylor's law and experiment with various classifiers to ident…
A new method for prioritizing sequences in reinforcement learning improves learning efficiency.
problem Efficient learning in reinforcement learning algorithms.
method Prioritized Sequence Experience Replay (PSER) for prioritizing sequences of experience.
result PSER is guaranteed to converge faster than PER and substantially improves performance.
Generative Adversarial Networks create realistic financial correlation matrices.
problem Creating realistic financial correlation matrices for practical applications.
method Generative Adversarial Networks (GANs) to model correlation matrices.
result GANs can recover known stylized facts about empirical correlation matrices.
New empirical PAC-Bayes bound for Markov chains with finite state space.
problem Lack of empirical bounds for Markov chains with temporal dependence.
method Proved a new PAC-Bayes bound for Markov chains, providing an empirical pseudo-spectral gap.
result First fully empirical PAC-Bayes bound for Markov chains with finite state space.
BERT outperforms traditional machine learning in text classification tasks.
problem Comparing BERT to traditional machine learning methods for text classification.
method Empirical testing of BERT against TF-IDF-based machine learning models in various scenarios.
result BERT demonstrates superior performance and independence from text features.
Proposes robust graph embedding with noisy link weights.
problem Learning feature vectors from noisy link weights.
method β-graph embedding with empirical moment β-score.
result Computational tractability and local minimization of β-score.
Empirical moment matrix reveals properties of point clouds.
problem Uncovering properties of point clouds, especially those with singular support.
method Combining statistics, real algebraic geometry, and approximation theory.
result The empirical moment matrix provides insights into data analysis.
New method estimates Schrödinger bridge potentials via empirical risk minimization.
problem Estimating Schrödinger bridge potentials from samples.
method Rewriting Schrödinger system as a fixed-point equation and estimating the potential via empirical risk minimization.
result Uniform concentration of empirical risk around population counterpart under sub-Gaussian assumptions.
CcGAN tackles conditional image generation for continuous labels.
problem Mathematical challenges in conditioning on continuous, scalar labels.
method Proposes novel empirical losses and label input methods for continuous conditional GANs.
result CcGAN generates diverse, high-quality images from continuous labels.
Proposes a more accurate random forest algorithm by selecting the best-performing trees.
problem Improving accuracy in binary classification problems.
method Best-scored random forest: selects the best-performing tree from random candidates.
result The best-scored random forest can be more accurate than the original random forest.
The paper provides convergence guarantees for multicalibration gradient boosting.
problem Understanding the convergence properties of multicalibration gradient boosting.
method Computational guarantees for multicalibration gradient boosting algorithms, including adaptive variants.
result The magnitude of successive prediction updates decays at O ( 1 / T ) O(1/\sqrt{T}) O ( 1/ T ) , leading to convergence in empirical multicalibration error. A novel framework optimizes experience replay for reinforcement learning.
problem Optimizing the replay policy for better performance in off-policy reinforcement learning.
method Proposes a novel ERO framework that alternately updates the agent policy and replay policy.
result Demonstrates improved performance in various continuous control tasks.
A new SGD framework reduces empirical risk by favoring higher loss observations.
problem Minimizing empirical risk in machine learning problems.
method Develops a biased gradient estimator for stochastic optimization.
result Minimizes an ordered modification of the empirical average loss.
New method approximates high-dimensional probability densities efficiently.
problem Approximating high-dimensional probability densities accurately and efficiently.
method Hierarchical tensor-network approach using randomized SVD and linear equations.
result The method effectively approximates high-dimensional densities with linear complexity.
Review of quantile regression methods for stochastic computer experiments.
problem Quantile regression in stochastic computer experiments.
method Six metamodels categorized by order statistics, functional approaches, and Bayesian methods tested on various problems.
result Metamodels reveal good contrasts, providing guidelines for selecting the best method.
A new DP algorithm for weighted ERM protects sensitive data in predictive models.
problem Protecting sensitive personal information in predictive models trained via ERM.
method Proposes the first differentially private algorithm for weighted ERM with formal privacy guarantees.
result Demonstrates strong DP guarantees while maintaining robust performance in real-world data.
Study of 40+ complexity measures in 10,000 deep networks.
problem Generalization of deep networks in various settings.
method Systematic study of 10,000 convolutional networks with varied hyperparameters.
result Surprising failures and promising measures for further research.
Meta-learning bounds derived using PAC-Bayes theory for improved generalization.
problem Uncertainty in generalization performance for meta-learning with new tasks.
method PAC-Bayes relative entropy bounds and empirical risk minimization (ERM) method.
result Competitive generalization performance and rapid convergence with data-dependent prior.
New insights into experience replay in RL algorithms.
problem Understanding the impact of replay capacity and replay ratio in Q-learning.
method Systematic and extensive analysis of experience replay in Q-learning methods, focusing on replay capacity and replay ratio.
result Greater replay capacity significantly improves performance for certain algorithms, while other techniques offer limited benefit.
This paper improves random feature sampling using empirical leverage scores.
problem Optimizing the number of features for kernel approximation and supervised learning.
method Uses empirical leverage scores to optimize feature sampling.
result Empirical sampling of random features using leverage scores outperforms vanilla Monte Carlo sampling.
Recently, a unified model for image-to-image translation tasks within adversarial learning framework has aroused widespread research interests in computer vision practitioners. Their reported empirical success however lacks solid theoretical interpretations for its inherent mechanism. In this paper, we reformulate thei…
Improves deep transfer learning by preventing performance degradation.
problem Deep transfer learning can degrade performance when using inappropriate pre-trained weights.
method Proposes a novel strategy to compute new descent directions that preserve regularization effects.
result DTNH strategy improves performance of deep transfer learning tasks by 0.1%--7%.
Develops an efficient method for large-scale deep learning problems.
problem Efficiently addressing the computational and memory challenges of natural gradient methods in deep learning.
method Randomized techniques for sketching the empirical Fisher information matrix in neural network layers.
result Global convergence to stationary points and fast linear convergence under the NTK case.
Empirical study shows interpretable gradients improve adversarial robustness.
problem Connecting adversarial robustness and model interpretability.
method Introduced Interpretation Regularization (IR) to encourage interpretable gradients.
result Training models to have interpretable gradients improves adversarial robustness.
Study compares different covariance estimation methods for portfolio allocation.
problem Comparing methods for estimating covariance and precision matrices in portfolio allocation.
method Gaussian Graphical Model (GGM), Shrinkage, Thresholding, Random Matrix Theory (RMT) methods.
result GGM methods outperform other methods in predictive ability for portfolio allocation.
Framework uses experience replay to prevent deep networks from forgetting past tasks.
problem Deep networks forget past tasks after learning new ones in sequential multitask learning.
method Generative model that couples current task with past learned tasks through a discriminative embedding space.
result Framework learns a shared abstract distribution across all tasks, preventing catastrophic forgetting.
Efficient actor-critic learning with shared experience replay improves data efficiency.
problem Challenges in actor-critic reinforcement learning with experience replay and off-policy learning stability.
method Combining actor-critic algorithms with shared experience replay, analyzing V-trace, proposing a trust region scheme.
result State-of-the-art data efficiency on Atari achieved with 200M environment frames.
Reweighting improves risk bounds in certain data regions.
problem Improving risk bounds in classification and heteroscedastic regression.
method Weighted empirical risk minimization with a data-dependent weight function.
result A weighted ERM estimator can achieve superior performance in specific sub-regions.
New method balances covariates for stable causal survival effect estimation.
problem Estimating causal survival effects in data with conditionally-independent censoring.
method Covariate-balancing approach to empirically stable and asymptotically efficient estimation.
result Validated theoretical results in synthetic and semi-synthetic data.
Bayesian Empirical Bayes extends EB to complex structures using probabilistic symmetry.
problem Improving simultaneous inference in complex settings like arrays and graphs.
method Generalized empirical Bayes approach based on probabilistic symmetry.
result BEB outperforms existing methods in denoising arrays and spatial data.
We solve robust optimization problems using Wasserstein balls and apply it to mean-CVaR optimization.
problem Distributionally robust optimization with Wasserstein ambiguity sets.
method Transformed robust optimization into non-robust with penalty term, selecting ambiguity set size.
result Impressive results in robust mean-CVaR optimization compared to other strategies.
Mitigates overfitting in UU classification from two unlabeled datasets.
problem Overfitting in the UU classification method.
method Wrapping negative empirical risk terms with correction functions and proving consistency.
result Successfully mitigates overfitting and improves classification accuracy.
RER improves sample complexity by updating in reverse order.
problem Theoretical analysis limits RER's convergence rate.
method Tighter analysis for larger learning rates and longer sequences.
result RER converges faster with larger learning rates and longer sequences.
The paper analyzes high-dimensional linear regression using parametric empirical Bayes methods.
problem Estimation of i.i.d. priors in high-dimensional Bayesian linear regression with random design.
method Parametric empirical Bayes estimation, variational lower bound maximization, phase transition analysis.
result The vEB estimator is information theoretically optimal up to p = o ( n 2 / 3 ) p=o(n^{2/3}) p = o ( n 2/3 ) but sub-optimal in higher dimensions. A new score measures data reliability without ground truth.
problem Assessing reliability of datasets without access to ground truth.
method Define ground-truth-based orderings and propose Gram determinant score.
result Gram determinant score effectively captures data quality across diverse observation processes.
Study finds LLMs hallucinate in finance tasks, needing research.
problem Hallucination in LLMs in finance.
method Empirical investigation of four methods to mitigate hallucination.
result LLMs hallucinate in financial tasks.