New algorithm learns disjunctions faster than previous methods.
problem Learning Boolean disjunctions in the agnostic PAC model.
method Developed an agnostic learner with complexity 2ildeO(n1/3). result First separation between SQ and CSQ models in distribution-free agnostic learning.
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.
Boosts weak online learners to strong ones with sublinear regret.
problem Online learning agnostic setting without strong guarantees.
method Reduction to online convex optimization, boosting via marginally-better-than-trivial regret guarantees.
result First agnostic online boosting algorithm with sublinear regret.
This paper develops dimension-agnostic inference methods for high-dimensional data.
problem Understanding how classical inference methods behave in high-dimensional settings.
method Using variational representations, sample splitting, and self-normalization to create a refined test statistic.
result The resulting statistic has a Gaussian limiting distribution regardless of how dimensionality scales with sample size.
New insights into RL with weak function approximation.
problem Statistical complexity of RL with function approximation in large state spaces.
method Agnostic policy learning framework, exploring environment access, coverage, and representational conditions.
result Characterization of fundamental performance bounds and statistical separations.
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.
A new framework for brain mapping using statistical agnostic methods.
problem Estimating brain connectivity with limited data and controlling false positives.
method Statistical Agnostic Mapping (SAM) based on concentration inequalities.
result Relieves instability and provides less conservative p-value correction.
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.
SAR evaluates ML-based linear regression models for statistical significance.
problem Lack of formal statistical significance in ML-based regression models.
method Statistical Agnostic Regression (SAR) using concentration inequalities and worst-case scenario analysis.
result SAR provides a threshold for statistical significance without assuming underlying assumptions.
New SQ lower bound shows complexity nearly matches known upper bound for smoothed agnostic learning.
problem Smoothed agnostic learning of halfspaces under subgaussian distributions.
method Statistical Query (SQ) lower bound using moment-matching hard distribution and linear programming duality.
result First non-trivial lower bound on complexity nearly matches known upper bound.
New bounds show complex neural networks need many queries to learn.
problem Learning non-polynomial activation functions with Gaussian marginals.
method Gradient boosting procedure to amplify lower bounds on SQ dimension of neural networks.
result Statistical-query lower bounds for ReLU regression with 2ncε queries. Task-agnostic data valuation without validation requirements.
problem Valuing data without specific task assumptions.
method Estimating data diversity and relevance through queries without raw data.
result Estimates capture the diversity and relevance of seller's data for the buyer.
New complexity measure helps in agnostic reinforcement learning with or without access to MDP dynamics.
problem Understanding the number of rounds needed to learn an ε-suboptimal policy in unknown MDPs.
method Introducing spanning capacity as a new complexity measure and developing POPLER algorithm.
result There is a separation between generative and online access models for agnostic learnability.
We clarify measurability assumptions in the agnostic PAC learning theorem.
problem Measurability assumptions in the Fundamental Theorem of Statistical Learning.
method Measure-theoretic scrutiny of existing proofs to extract minimal assumptions.
result Sound statement and detailed proof of the Fundamental Theorem in the agnostic setting.
Novel framework for ML-assisted inference valid for any statistical task.
problem Limited validity of existing methods for post-prediction inference.
method Introduces PSPS framework for task-agnostic ML-assisted inference.
result Valid and efficient inference for arbitrary ML models.
Paper develops PAC verification for hypothesis classes and statistical algorithms.
problem Verifying machine learning models interactively.
method Develops interactive proof for PAC verification, proves lower bounds, and introduces a generalization.
result Improved protocol for verifying unions of intervals and statistical query algorithms.
Paper achieves fast learning rates without margin assumptions in agnostic settings.
problem Learning fast rates in the agnostic setting without margin assumptions.
method Proposes a specific learning algorithm for classification with a reject option.
result Achieves a learning rate of $O\left(\frac{d}{n}\log \frac{n}{d}
ight)$ in the agnostic setting.
Simple methods combine statistical tests for out-of-distribution detection.
problem Detecting data points not following the training distribution.
method Combining classical parametric tests (Rao's score test) and a typicality test.
result Combining Fisher's method of test statistics improves out-of-distribution detection accuracy.
Paper analyzes error exponent in agnostic PAC learning.
problem Analyzing performance of agnostic PAC learning.
method Using error exponent from Information Theory to analyze PAC learning.
result Improved distribution-dependent error exponent for agnostic learning.
Paper proves optimality of doubly robust estimators for treatment effects.
problem Estimating treatment effects in causal inference.
method Structure-agnostic framework of statistical lower bounds, using non-parametric regression and classification oracles.
result Doubly robust estimators are statistically optimal for ATE and ATT.
Gradient EM converges exponentially to optimal solution in agnostic mixtures.
problem Fitting k parametric functions to given data points without a generative model. method Gradient EM algorithm for agnostic mixtures of arbitrary parametric functions.
result Gradient EM converges exponentially to population loss minimizers with high probability.
Study shows depth improves generalization in deep learning models.
problem Understanding why and when depth improves generalization in deep learning.
method Implementation-agnostic state-transition model to analyze depth and generalization.
result Identifies geometric and semigroup mechanisms that keep entropy contribution saturated or polynomial, clarifying depth's statistical advantage.
Unified framework for realizable and agnostic learning.
problem Lack of a unified theory for realizable and agnostic learnability.
method Three-line blackbox reduction.
result Unified understanding across various learning settings.
Paper analyzes agnostic learning of mixed linear regression without generative models.
problem Learning mixed linear regression without assuming stochastic generation.
method Expectation Maximization (EM) and Alternating Minimization (AM) algorithms.
result AM and EM algorithms converge to population loss minimizers under standard conditions.
New algorithm reduces prediction error in online learning without knowing base measure.
problem Smoothed online learning without knowledge of base measure.
method R-Cover algorithm based on recursive coverings.
result First algorithm to guarantee sublinear regret for agnostic smoothed online learning without prior knowledge of base measure.
Study learning and refutation in non-interactive LDP, showing sample complexity equivalence.
problem Characterize sample complexity for learning and refutation in non-interactive LDP.
method Characterize sample complexity for agnostic PAC learning in non-interactive LDP protocols.
result Optimal sample complexity for any concept class is captured by the approximate γ2~norm of a natural matrix associated with the class. RelEx explains relational models without gradient access.
problem Lack of explainability for relational models like GNNs and SRL.
method Model-agnostic explainer for relational models using only outputs.
result Comparable or better performance compared to GNN-Explainer.
Global watermark for diffusion language models decouples detection from local contexts.
problem Watermarking in diffusion language models is challenging due to joint sampling of distributions over many unresolved positions.
method Proposes a global vector-valued sketch representation to control watermarking in masked diffusion language models.
result The method decouples detection from local contexts, resulting in an order-agnostic statistic and robustness.
Conformal prediction offers distribution-free inference for complex models.
problem Traditional predictive inference methods are limited by assumptions about data distributions and model details.
method Conformal prediction uses symmetry assumptions and treats learning algorithms as black boxes.
result Conformal prediction provides exact finite-sample guarantees, even under limited assumptions.
Paper proposes a hybrid RL algorithm that combines offline and online data without needing reward info.
problem How to efficiently use online data to improve RL policies using only offline data.
method A three-stage hybrid RL algorithm that uses reward-agnostic exploration and model-based offline RL.
result The hybrid RL algorithm outperforms both pure offline and pure online RL in sample complexity.
Task-agnostic RL tackles exploration in MDPs with multiple tasks.
problem Challenges in reinforcement learning with multiple tasks or conflicting objectives.
method Task-agnostic RL framework, UCBZero algorithm.
result UCBZero finds near-optimal policies for multiple tasks efficiently.
New bounds show agnostic multiclass learning depends on two dimensions: Natarajan and Daniely-Shalev-Shwartz.
problem Understanding sample complexity in multiclass classification with agnostic learning.
method Developed a novel online procedure based on a self-adaptive multiplicative-weights algorithm.
result Agnostic sample complexity bounds are in the form of DS^(1.5)/ε + Nat/ε^2, nearly tight up to a √DS factor.
Paper tackles label noise in large datasets, purifying noisy data with a nonparametric framework.
problem Label noise in large-scale datasets with coarse labels.
method Develops a model-agnostic nonparametric framework for classification.
result Framework purifies noisy data using a small clean dataset and manages ambiguous samples.
We study high-dimensional distribution learning in an agnostic setting where an adversary is allowed to arbitrarily corrupt an ε-fraction of the samples. Such questions have a rich history spanning statistics, machine learning and theoretical computer science. Even in the most basic settings, the only known…
TAME learns new tasks without knowing them, outperforming existing methods.
problem Learning new tasks without task identities.
method TAME detects task shifts using loss function deviations and employs online pruning.
result TAME outperforms existing methods on continual learning benchmarks.
LARP filters data to protect model performance across various learners.
problem Protecting model accuracy in public datasets with diverse learners.
method Formalizes and analyzes LARP, a robust data prefiltering method.
result LARP provides guarantees on worst-case loss over a set of learners, with some performance trade-off.
Robust learner finds subspace for MIMs with label noise.
problem Learning Multi-Index Models with label noise under Gaussian distribution.
method Iterative subspace approximation using conditional moments.
result Qualitatively optimal robust learner in SQ model.
New statistical guarantee improves conformal predictors for small datasets.
problem Uncertainty quantification for small datasets in surrogate models.
method Proposed a new statistical guarantee for conformal predictors, converging to standard CP for large datasets.
result The new guarantee offers relevant information about coverage for small data sizes, improving applicability.
A new method for predicting insurance claims with statistical guarantees.
problem Creating accurate prediction intervals for insurance claims.
method Model-agnostic framework using split conformal prediction for frequency-severity modeling.
result Shows effectiveness on simulated and real datasets using various models.
Theory establishes optimal rates for estimating linear functionals without structural assumptions.
problem Estimating linear functionals of unknown nuisance components without structural assumptions.
method Structure-agnostic framework, doubly robust estimators, first-order debiasing.
result Characterization of minimax optimal rates and regimes for double robustness.
Double Machine Learning estimators are asymptotically inadmissible under structure-agnostic models.
problem Minimax estimators may be inadmissible under structure-agnostic models.
method Exhibit second-order (U-statistic) estimators that asymptotically dominate DML estimators.
result Double Machine Learning estimators are asymptotically inadmissible under structure-agnostic 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.
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.
Hierarchical-CPI improves variable importance measurement for medical data.
problem Limited interpretability of complex medical models.
method Hierarchical-CPI measures conditional variable importance with statistical control, handling correlated data.
result Hierarchical-CPI outperforms existing methods in medical datasets.
Study efficient estimation of hidden subspaces in Gaussian Multi-index models.
problem Estimating hidden subspaces in Gaussian Multi-index models with low-dimensional projections.
method Introduced the generative leap exponent and developed an agnostic sequential estimation procedure using spectral U-statistics.
result Achieved optimal sample complexity of $n=Θ(d^{1 \vee \k/2})$ for efficient estimation.
Efficiently learns complex Boolean functions under Gaussian distributions.
problem Learning complex Boolean functions of halfspaces under Gaussian marginals.
method First efficient proper agnostic learning algorithm for arbitrary Boolean functions of K halfspaces.
result Matches the best known improper learning algorithm's run-time dependence on dimension.
We establish a tight characterization of the worst-case rates for the excess risk of agnostic learning with sample compression schemes and for uniform convergence for agnostic sample compression schemes. In particular, we find that the optimal rates of convergence for size-k agnostic sample compression schemes are of…