New algorithm for reliable learning of Gaussian halfspaces with improved sample and computational complexity.
problem Learning halfspaces under Gaussian marginals with reliable agnostic model.
method Developed a new algorithm for reliable learning of Gaussian halfspaces with specific sample and computational complexity.
result Achieved a new algorithm with improved sample and computational complexity for reliable learning of Gaussian halfspaces.
WISCA generates consensus explanations from conflicting model-agnostic interpretability methods.
problem Conflicting explanations from diverse interpretability algorithms.
method WISCA integrates class probability and normalized attributions to generate consistent explanations.
result WISCA consistently aligns with the most reliable individual method, improving explanation reliability.
MAntRA combines machine learning and Bayesian methods for time-dependent reliability analysis of unknown systems.
problem Time-dependent reliability analysis of systems with unknown governing physics.
method Combines machine learning, Bayesian statistics, and stochastic integration to discover and analyze SDEs from data.
result Demonstrates the effectiveness of MAntRA on three numerical examples, indicating its potential for in-situ and heritage structure analysis.
New algorithm reliably learns ReLU functions efficiently.
problem Learning ReLU functions in the Reliable Agnostic model.
method Combines kernel methods, polynomial approximations, and dual-loss approach.
result First efficient algorithms for reliable learning of ReLU functions.
MAPS algorithm creates reliable prediction intervals for high-dimensional data.
problem Computing reliable conditional prediction intervals in high-dimensional settings.
method Lifted predictive model (LPM) and MAPS algorithm for distribution-free intervals.
result MAPS algorithm produces valid prediction intervals for any trained model.
SMART simplifies data labeling for machine learning.
problem Creating labeled training data for machine learning.
method Intuitive web interface, active learning, inter-rater reliability.
result Reduces the need for labeled data and improves label quality.
New method quantifies model complexity for better interpretation.
problem Complex models produce misleading interpretation results.
method Functional decomposition to quantify model complexity.
result Post-hoc interpretation of complex models is more reliable and compact.
Algorithm learns binary function efficiently under arbitrary covariate shift.
problem Learning binary function under arbitrary distributions P and Q.
method PQ-learning algorithm using reliable learner with selective classification.
result Polynomial-time algorithm for covariate shift learning.
Classical clients can verify quantum learning tasks efficiently.
problem Making quantum learning accessible to classical clients.
method Developed a framework for classical verification of quantum learning.
result Quantum learning tasks can be efficiently verified by classical verifiers.
A new sampling strategy improves reliability and robustness optimization for complex designs.
problem High sample requirements for optimizing reliability and robustness in complex designs.
method Local Latin Hypercube Refinement (LoLHR) for multi-objective design uncertainty optimization.
result LoLHR achieves better results compared to other surrogate-based strategies.
Cluster LOCO: A model-agnostic feature importance score for interpreting cluster outputs
problem Interpreting and auditing cluster outputs
method Cluster LOCO (Leave-One-Covariate-Out)
result More reliably recovers informative features than existing methods
A new method calibrates value predictions in offline RL to improve reliability.
problem Difficulty in long-horizon value prediction in offline reinforcement learning.
method Bellman calibration, a weak reliability criterion, and Iterated Bellman Calibration.
result Finite-sample guarantees show that Bellman calibration error is controlled at nonparametric rates.
LIME explanations can be uncertain, even for accurate models.
problem Uncertainty in LIME explanations undermines trust in machine learning models.
method Demonstrated two sources of uncertainty in LIME: sampling randomness and varying interpretation quality.
result Uncertainty in LIME explanations is present even in high-performing models.
CDLEEDS detects local changes in evolving data streams for accurate feature attributions.
problem Local feature attributions become obsolete in evolving data streams.
method CDLEEDS, a flexible framework for detecting local change and concept drift.
result CDLEEDS reliably detects both local and global concept drift.
Combines machine learning and data assimilation for improved forecasting.
problem Improving forecast accuracy with noisy observations.
method Sequentially learns a machine-learning model using an ensemble Kalman filter.
result The combined model achieves good forecast skill and computational efficiency.
New method learns robot actions from videos without explicit labels.
problem Training robots to perform tasks from few demonstrations.
method Uses images and text for task-agnostic and general representation, synthesizes hallucinated actions, and applies dense correspondences.
result Trains robot policies solely from RGB videos, achieving diverse tasks across different robots and environments.
Kernel methods accurately predict Hamiltonian systems from data.
problem Data-driven simulation of Hamiltonian systems.
method Two-step and one-step kernel-based methods for identifying and forecasting Hamiltonian systems.
result Framework achieves accurate, data-efficient predictions across various benchmark systems.
Risk Advisor predicts and mitigates ML deployment failures.
problem Predicting and mitigating test-time failure risks of ML systems.
method Post-hoc meta-learner for estimating failure risks and uncertainties.
result Reliably predicts deployment-time failure risks across various ML models.
This paper tackles online reinforcement learning for unseen tasks with unknown boundaries.
problem Real-world tasks violate assumptions of task distributions, independence, and clear task delineations.
method A mixture of Gaussian Processes models different dynamics, and a transition prior handles temporal dependencies.
result The approach reliably handles task distribution shifts and outperforms alternatives in non-stationary tasks.
Proposes a method to improve CATE estimation by imputing missing potential outcomes.
problem Statistical discrepancy between distinct treatment groups in CATE estimation.
method Contrastive learning approach to reliably impute missing potential outcomes for a subset of individuals.
result Improves the accuracy and robustness of CATE estimation models.
First proper learning algorithm for Gaussian halfspaces with matching sample and computational complexity.
problem Agnostically learning halfspaces under Gaussian distribution.
method First proper learning algorithm with matching sample and computational complexity.
result First proper learning algorithm for agnostically learning halfspaces under Gaussian distribution with matching sample and computational complexity.
New bounds found for agnostic learning with sample compression schemes.
problem Finding optimal rates of convergence for agnostic learning.
method Established tight characterization of worst-case rates for agnostic learning with sample compression schemes.
result Optimal rates of convergence for size- k k k agnostic sample compression schemes are k log ( n / k ) n \sqrt{\frac{k \log(n/k)}{n}} n k l o g ( n / k ) . A framework for detecting out-of-distribution data in RL using uncertainty-based classification.
problem Detecting out-of-distribution data in deep reinforcement learning systems.
method A one-class classification problem approach based on epistemic uncertainty reduction.
result The proposed UBOOD framework reliably detects out-of-distribution situations when combined with ensemble-based uncertainty estimators.
LUNO linearizes neural operators to quantify their predictive uncertainty.
problem Quantifying the predictive error of neural operators for high-stakes simulations.
method Model linearization to push weight-space uncertainty forward to predictions.
result LUNO provides a practical and theoretically sound way to apply Bayesian methods to neural operators.
PredDiff measures prediction changes while marginalizing features, offering new insights into interaction effects.
problem Understanding interaction effects in black-box models.
method Model-agnostic, local attribution method based on probability theory.
result Introduced a new measure for interaction effects between arbitrary feature subsets.
New framework controls FDR for grouped features in sequential models.
problem FDR control for grouped features in sequential models.
method Grouped-feature FDR control framework for sequential and grouped models using mirror statistics and Permutation SHAP.
result FDR control for low- and high-dimensional grouped linear models and improved power under correlated signals.
STOIC improves energy demand forecasting with reliable uncertainty estimates.
problem Accurate point forecasts alone are insufficient for energy systems; reliable uncertainty estimates are needed.
method Integrates graph-based forecasting with tabular foundation models for zero-shot calibration of spatial-temporal residuals.
result STOIC delivers more reliable and robust uncertainty estimates for complex graph-structured energy time series.
The study optimizes polynomial regression for learning under Gaussian distributions.
problem Agnostic learning of Boolean and real-valued functions under Gaussian distributions.
method LP duality and polynomial degree analysis for L 1 L^1 L 1 -regression. result Optimal SQ lower bounds for various function classes.
New algorithm learns disjunctions faster than previous methods.
problem Learning Boolean disjunctions in the agnostic PAC model.
method Developed an agnostic learner with complexity 2 i l d e O ( n 1 / 3 ) 2^{ ilde{O}(n^{1/3})} 2 i l d e O ( n 1/3 ) . result First separation between SQ and CSQ models in distribution-free agnostic learning.
TRIP detects unreliable feature importance scores in random forests.
problem Unreliable feature importance scores in random forests due to model extrapolation.
method Develops TRIP (Test for Reliable Interpretation via Permutation) to detect unreliable permutation feature importance scores.
result TRIP reliably detects unreliable permutation feature importance scores in high-dimensional settings.
New algorithms save computation in agnostic learning with membership queries.
problem Efficiently learning touchstone classes with membership queries.
method Designing agnostic learning algorithms for circuits with sublinear gates.
result Agnostic learning algorithms for circuits with sublinear gates achieve significant computational savings.
Proposes integrating global and local entropy for more reliable LLMs.
problem Uncertainty in large language models (LLMs) leads to unreliable predictions.
method Measures global uncertainty from hidden-state matrices and local uncertainty from tokens, combining them via a multiplicative gate.
result Global-Local Uncertainty (GLU) outperforms unsupervised baselines across multiple models and benchmarks.
Extends boosting to multiclass online agnostic classification.
problem Online multiclass classification with weak learners.
method Reduces multiclass online agnostic boosting to online convex optimization.
result First boosting algorithm for online agnostic multiclass classification.
New algorithms improve agnostic learning for triangles and polygons, reducing time complexity.
problem Efficient agnostic learning for geometric concept classes.
method Data structures and algorithms from computational geometry, probabilistic combinatorics.
result Optimal time complexity improvements for agnostic learning of triangles and polygons.
Improves model-based control and exploration by estimating model uncertainty.
problem Inaccuracies in model predictions lead to frequent re-planning, inefficiency, and unreliability.
method Estimates model uncertainty using reconstruction error and uses it for better control and active exploration.
result Improves control performance and exploration efficiency by choosing confident model predictions and planning for high uncertainty.
New bounds for agnostic learning with average smoothness.
problem Distribution-free nonparametric regression with average smoothness.
method Distribution-free uniform convergence bounds and agnostic learning algorithm.
result Distribution-free uniform convergence bounds for average-smoothness classes in the agnostic setting.
A new method for feature importance inference without data splitting.
problem Feature importance inference for machine learning models.
method Minipatch ensembles for model-agnostic, distribution-free inference.
result Asymptotic validity of confidence intervals without data splitting.
Study shows transductive learning is equivalent to PAC learning for most natural loss functions.
problem Understanding the relationship between transductive and PAC learning models.
method Extending existing results and developing new techniques to analyze the equivalence of the two models.
result Transductive learning is essentially equivalent to PAC learning for realizable learning with most natural loss functions.
ATAML improves text classification with attention mechanisms.
problem Limited deep learning performance with scarce data.
method Meta-learning with attention mechanisms.
result ATAML outperforms other methods on text classification tasks.
Query access significantly speeds up learning Multi-Index Models under Gaussian distribution.
problem Agnostically learning Multi-Index Models (MIMs) under Gaussian distribution.
method Query access for MIMs with complexity O ( k ) p o l y ( 1 / ε ) p o l y ( d ) O(k)^{\mathrm{poly}(1/ε)} \; \mathrm{poly}(d) O ( k ) poly ( 1/ ε ) poly ( d ) under standard regularity assumptions. result Query access gives significant runtime improvements over random examples for agnostically learning MIMs.
Boosting with unlabeled data achieves optimal sample complexity in agnostic settings.
problem Boosting's sample inefficiency in agnostic learning.
method Designing an agnostic boosting algorithm with unlabeled data to match ERM's sample complexity.
result The total sample complexity is optimal, with a vanishing fraction needing to be labeled.
EAGLE improves reproducibility and stability of model explanations.
problem Creating reliable explanations for opaque machine learning models.
method Formulates perturbation selection as an information-theoretic active learning problem.
result EAGLE learns a linear surrogate model with feature importance scores and uncertainty estimates.
Estimates mean and covariance from noisy data without knowing the noise type.
problem Estimating mean and covariance from noisy data with unknown noise type.
method Polynomial-time algorithms for agnostic estimation.
result Achieves error guarantees in terms of information-theoretic lower bounds.
OTAD uses optimal transport to create robust models against adversarial attacks.
problem Vulnerability of deep neural networks to adversarial perturbations.
method OTAD combines optimal transport and Lipschitz networks to create a robust model.
result OTAD outperforms other robust models on diverse datasets.
Study agnostic RL in large state spaces with weak function approximation.
problem Statistical intractability of agnostic policy learning in various environments.
method Investigates agnostic policy learning with different forms of environment access.
result Agnostic policy learning remains statistically intractable with certain forms of environment access.
Improved agnostic learning time via Gaussian surface area analysis.
problem Learning polynomial threshold functions under Gaussian marginals.
method Improvement of polynomial degree required for approximation.
result Near optimal bounds on agnostic learning complexity.
This paper studies universal rates of ERM for binary classification under agnostic learning.
problem The challenge of achieving universal rates of ERM for binary classification under agnostic learning.
method The paper explores the agnostic universal rates of ERM for binary classification, revealing three possible rates: e − n e^{-n} e − n , o ( n − 1 / 2 ) o(n^{-1/2}) o ( n − 1/2 ) , or arbitrarily slow. result The paper provides a complete characterization of which concept classes fall into each of the three categories of agnostic universal rates.
Study shows realizable learnability doesn't imply agnostic learnability for distributions.
problem Learnability and robustness of distribution classes.
method Analyzes the relationship between learnability and robustness for distribution learning.
result Realizable learnability does not imply agnostic learnability for distributions.