New oracle uses uncertainty for active classification with noisy feedback.
problem Improving query complexity in interactive binary classifier learning.
method Proposes a new pairwise comparison oracle that considers uncertainty and an adaptive labeling algorithm.
result Demonstrates improved performance and efficiency compared to existing methods.
Pairwise "same-cluster" queries are one of the most widely used forms of supervision in semi-supervised clustering. However, it is impractical to ask human oracles to answer every query correctly. In this paper, we study the influence of allowing "not-sure" answers from a weak oracle and propose an effective algorithm …
Paper addresses online alignment of large language models under uncertain preference feedback.
problem Online alignment of large language models with misspecified preference feedback.
method Formulates an oracle-robust objective as a worst-case optimization problem for log-linear policies, and develops projected stochastic composite updates.
result Shows that the robust objective admits an exact closed-form decomposition and achieves O ~ ( ε − 2 ) \widetilde{O}(\varepsilon^{-2}) O ( ε − 2 ) oracle complexity. This technique learns interpretable models by encoding the training distribution as a Dirichlet Process and using uncertainty scores as an oracle.
problem Creating small, interpretable models that are still accurate.
method Exploits a Dirichlet Process to encode the training distribution, uses Bayesian Optimization for parameters, and projects data to one dimension using an uncertainty oracle.
result Improves accuracy and size trade-off, applicable across different model families.
Study examines how uncertainty visualization affects analyst trust in automated classification systems.
problem The impact of uncertainty on analyst trust in automated classification systems.
method Empirical study evaluating different active learning query policies and visualizations.
result Query policy significantly influences analyst trust in automated classification systems.
Semi-supervised active clustering (SSAC) utilizes the knowledge of a domain expert to cluster data points by interactively making pairwise "same-cluster" queries. However, it is impractical to ask human oracles to answer every pairwise query. In this paper, we study the influence of allowing "not-sure" answers from a w…
Paper tackles NNS under uncertainty with improved algorithms.
problem Efficient nearest neighbor search with noisy distance estimates.
method Combines cover trees and multi-armed bandits for optimal performance.
result Optimal dependence on dataset size and unknown geometry achieved.
Proposes a new model to generate informative samples for image classification without querying an oracle.
problem Expensive and difficult labeling of data for machine learning models.
method Integrates active learning with a conditional GAN to generate samples with high uncertainty for a specific label.
result Generated samples improve image classification performance without querying an oracle.
A new Thompson Sampling framework handles uncertainty by imputing missing data.
problem Handling uncertainty in contextual bandit problems.
method Generative model to impute missing outcomes, fit policy, and select actions.
result Established a state-of-the-art regret bound that depends on generative model quality.
New algorithm learns POMDPs without computational oracles.
problem Learning near-optimal policies in POMDPs with computationally hard oracles.
method Quasipolynomial-time algorithm using barycentric spanners for policy covers.
result First oracle-free learning algorithm for observable POMDPs.
CJE calibrates cheap LLM judges against an oracle, achieving high accuracy at a fraction of the cost.
problem Inexpensive LLM judges can produce biased rankings, leading to unreliable outcomes.
method CJE uses a small oracle to calibrate cheap scores, then evaluates at scale with valid uncertainty.
result CJE achieves 99% pairwise ranking accuracy at 14x lower cost compared to a 16x oracle/judge cost ratio.
We study contextual linear bandit problems under feature uncertainty, where the features are noisy and have missing entries. To address the challenges posed by this noise, we analyze Bayesian oracles given the observed noisy features. Our Bayesian analysis reveals that the optimal hypothesis can significantly deviate f…
ACFS optimizes spectral risk under decision-dependent uncertainty using adaptive forest sampling.
problem Minimizing spectral risk with decision-dependent uncertainty.
method ACFS integrates Generalised Random Forests, CEM-guided exploration, rank-weighted augmentation, and multi-start refinement.
result ACFS achieves lowest median oracle spectral risk on both benchmarks.
Bayesian-guided method selects optimal design from large candidate pool.
problem Optimizing complex structures with high-fidelity evaluations.
method Bayesian active learning with surrogate modeling.
result Optimal design identified with minimal oracle evaluations.
New algorithm learns FMDP structure while minimizing regret.
problem Regret minimization in FMDPs with unknown structure.
method Optimism in face of uncertainty principle combined with statistical structure learning.
result First algorithm to learn FMDP structure while minimizing regret.
PCS-UQ framework improves uncertainty quantification for machine learning models.
problem Ensuring trustworthy uncertainty quantification for machine learning models in high-stakes domains.
method PCS-UQ framework based on Predictability, Computability, and Stability principles, integrating prediction-checking, bootstrap samples, and multiplicative calibration.
result PCS-UQ maintains target coverage while outperforming or matching conformal methods in interval width and subgroup coverage.
A Bayesian approach to multilabel classification using tree-based models.
problem Challenges in multilabel classification due to complex label relationships and correlations.
method Bayesian Additive Regression Trees (BART) framework for modeling multilabel classification.
result Improved predictive performance compared to other models, including an oracle model.
QActor optimizes learning from noisy labeled data streams by querying experts for clean labels.
problem Learning from noisy labeled data in continuous streams with limited oracle queries.
method Combines quality models for filtering and oracle queries for true labels, dynamically adjusting query limits.
result QActor nearly matches optimal accuracy with up to 6% additional ground truth data from experts.
We develop a robust RL algorithm for off-dynamics environments with improved suboptimality bounds and computational efficiency.
problem Learning policies robust to uncertainties in transition dynamics between training and deployment environments.
method Distributionally robust Markov decision processes (DRMDPs) with a novel algorithm We-DRIVE-U.
result Improved suboptimality bound of O ~ ( d H ⋅ min { 1 / ρ , H } / K ) \widetilde{\mathcal{O}}\big({d H \cdot \min \{1/ρ, H\}/\sqrt{K} }\big) O ( d H ⋅ min { 1/ ρ , H } / K ) , near-optimal up to O ( H ) \mathcal{O}(\sqrt{H}) O ( H ) . Neural- σ 2 σ^2 σ 2 -LinearUCB improves regret in neural contextual bandits.
problem Balancing exploration and exploitation in neural contextual bandits.
method Proposes a variance-aware neural UCB algorithm using neural representations and an upper bound of reward noise variance.
result Oracle and practical versions of Neural- σ 2 σ^2 σ 2 -LinearUCB achieve better regret guarantees and performance. Improved stock selection through predictive fundamentals and uncertainty estimates.
problem Selecting stocks based on future financial data to outperform traditional factor models.
method Train deep nets to forecast future fundamentals, incorporate uncertainty estimates, and adjust portfolios to manage risk.
result Simulated annualized return of 17.7% and Sharpe ratio of 0.84 for uncertainty-aware model, significantly higher than 14.0% and 0.52 for standard factor models.
New approach optimizes decisions based on uncertainty in predictions.
problem Mismatch between prediction accuracy and decision loss in sequential design.
method Directional uncertainty-guided approach to sequential experimental design.
result Directional uncertainty-based design stops earlier and performs better.
Improves machine learning model training with noisy labels using active learning and clustering.
problem Training machine learning models with noisy oracles and limited data.
method Uses clustering and importance sampling to select batches of samples, incorporates model uncertainty, and introduces a denoising layer.
result Significant improvement in model accuracy on benchmark datasets compared to existing methods.
New methods improve graph classification accuracy using regional uncertainty.
problem Improving graph classification accuracy without labeled data.
method Proposed two new selection criteria for active learning: regional uncertainty and extended page-rank.
result Extended page-rank outperforms other methods when the fraction of labeled nodes is low.
Novel method to quantify aleatoric uncertainty of treatment effects from observational data.
problem Understanding randomness in treatment effects for medical treatments.
method Partial identification and Neyman-orthogonality to quantify aleatoric uncertainty.
result Developed a novel orthogonal learner (AU-learner) for quantifying aleatoric uncertainty.
Efficient Q-learning for metric spaces without planning oracles.
problem Efficient reinforcement learning in continuous state-action spaces.
method Model-free Q-learning adapted for metric spaces without a planning oracle.
result Sample efficiency in continuous state-action spaces.
Unified Bayesian-AI framework improves epidemiological risk prediction and uncertainty quantification.
problem Lack of calibrated uncertainty in machine learning models for epidemiology.
method Combines Bayesian prediction with Bayesian hyperparameter optimization using logistic regression and Gaussian-process Bayesian optimization.
result Unified Bayesian-AI framework provides reliable coverage and improved calibration, enhancing epidemiological decision making.
Active learning selects most informative unlabeled samples for labeling.
problem Efficiently label unlabeled data in applications with scarce labeled data.
method Formulated as open-set recognition, uses VNNs to identify uncertain samples.
result Achieved state-of-the-art results on MNIST, CIFAR-10, and CIFAR-100.
New principle optimizes bandit decisions with context.
problem Dealing with general function classes and large context spaces in bandits.
method Upper Counterfactual Confidence Bounds (UCCB) principle.
result Proves optimality and efficiency in complex settings.
Adaptive Bayesian learning aggregates experts to improve performance.
problem Bayesian online learning's performance depends on inferential choices.
method Treat Bayesian update rules as experts and aggregate them based on sequential predictive losses.
result The aggregate competes with the best expert in hindsight at a low aggregation cost.
The paper introduces algorithms for uncertainty quantification in metric spaces.
problem Uncertainty quantification in regression models defined on metric spaces.
method Proposes conformal and kNN prediction algorithms for metric spaces.
result Both algorithms provide finite-sample guarantees and improve local coverage calibration.
This thesis enhances ML reliability by selectively abstaining from predictions when uncertain.
problem Improving reliability in machine learning systems, especially in high-stakes domains.
method Exploiting uncertainty signals from training trajectories to develop lightweight, post-hoc abstention methods compatible with differential privacy.
result A robust trajectory-based approach to selective prediction that maintains high accuracy under privacy noise.
Improved MALA method for neural networks uncertainty quantification.
problem Uncertainty quantification in Bayesian neural networks.
method Corrected Stochastic MALA (csMALA) with a simplified correction term.
result Improved surrogate posterior for quantifying uncertainties in neural networks.
Proposes a weighted conformal approach for cluster label uncertainty.
problem Cluster label uncertainty in unlabeled data.
method Develops a conformal inference algorithm to correct label mismatch.
result Improves confidence set size in nonlinear and high-dimensional clustering.
New model-free RL algorithm tackles robust average-reward problems with finite sample complexity analysis.
problem Long-term decision-making in environments with varying dynamics.
method Proposes Robust Halpern Iteration (RHI) algorithm based on a black-box sampling oracle and multi-level Monte-Carlo estimator.
result Achieves ε-optimal robust policy with sample complexity of O(1/ε^(2+o(1))) under generative model setting.
Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.
problem Scalability issue in combinatorial semi-bandit problems due to high combinatorial optimization costs.
method Oracle-efficient frameworks that minimize oracle queries while maintaining tight regret guarantees.
result Achieved i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) regret with O ( log log T ) O(\log\log T) O ( log log T ) oracle queries for worst-case linear rewards. New analysis shows Thompson Sampling can work with greedy approximations in combinatorial bandits.
problem Thompson Sampling's theoretical limits with greedy approximations in combinatorial semi-bandits.
method Study with greedy oracle, providing lower and upper bounds on regret.
result First theoretical results showing TS can work with greedy approximations, breaking misconceptions.
Develops asymptotic theory for deep Cox models to enable valid inference.
problem Theoretical gaps in deep neural network estimators for Cox models.
method Asymptotic distribution theory linking in-sample optimization error to population risk.
result Pointwise and multivariate asymptotic normality for subsampled ensemble estimators.
Paper proposes a new method to minimize submodular functions with fewer calls to simpler oracles.
problem Minimizing the sum of submodular set functions with limited information.
method Introduces a modified convex problem requiring constrained total variation oracles that can be solved with fewer calls to minimization oracles.
result Shows significant reduction in the number of calls to minimization oracles.
New algorithms sample convex bodies using Markov chains and restricted Gaussian oracles.
problem Sampling uniformly from convex bodies efficiently.
method Markov chain Monte Carlo with proximal sampler and restricted Gaussian oracle.
result Efficient implementation of RGO for uniform sampling on convex bodies.
MAMBA learns policies competitive with multiple conflicting oracles.
problem Learning policies from multiple conflicting oracles in reinforcement learning.
method MAMBA uses a gradient estimator in the style of GAE to optimize policies, leveraging demonstrations from multiple weak oracles.
result MAMBA outperforms the state-of-the-art in learning policies competitive with multiple conflicting oracles.
We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder bu…
Quantum oracles help identify counterfactuals better than classical ones.
problem Identifying unknown causal parameters in causal models.
method Using quantum oracles to query and identify all causal parameters and counterfactuals.
result Quantum oracles enable identification of all two-way joint counterfactuals and tighter bounds on higher-order counterfactuals.
SoQal reduces oracle label requests in active learning by up to 35%.
problem Exploiting unlabelled data in healthcare requires costly oracle labeling.
method Dynamic questioning strategy to minimize oracle label requests.
result SoQal reduces oracle label requests by up to 35%.
Proposes a Bayesian framework for causal inference without explicit likelihood modeling.
problem Challenges in principled Bayesian inference for causal effects.
method Generalized Bayesian framework that places priors directly on causal estimands and updates using identification-driven loss functions.
result Yields generalized posteriors for causal effects with uncertainty quantification.
New oracles improve stochastic optimization with noisy or biased measurements.
problem Optimizing functions with noisy or biased measurements.
method Introduced biased gradient oracles for stochastic optimization, analyzed RSG and SGD algorithms with these oracles.
result Derived non-asymptotic bounds for convergence rates of algorithms with biased gradient oracles.
Algorithm solves online binary classification and infinite games using ERM oracle.
problem Online learning and solving infinite games with computationally inefficient oracles.
method Proposes an algorithm relying solely on ERM oracle calls for online binary classification and nonparametric games.
result Achieves finite and sublinearly growing regret in various settings.
New bounds on complexity for finding near-stationary points in stochastic convex optimization.
problem Finding near-stationary points in stochastic convex optimization.
method Joint analysis of local stochastic oracle and global oracle models; extensions of recursive regularization technique.
result Logarithmic dependence on smoothness in global oracle model for finding near-stationary points.