On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “Noisy Expert Feedback”

Selective Sampling and Imitation Learning via Online Regressioncs.LG

Interactive IL algorithm queries noisy expert for feedback, reducing sample size.

problem Imitation learning with noisy expert feedback requires many samples.

method Selective sampling algorithm with online regression oracle.

result Interactive IL algorithm reduces query complexity and improves performance.

Imitation Learning Selective Sampling Online Regression Noisy Feedback Interactive Algorithms

2023-07-11abs ↗pdf ↗

Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedbackcs.LG

New findings explain why online methods outperform offline methods in noisy expert feedback settings.

problem The challenge of learning from imperfect expert feedback in sequential decision-making systems.

method Introduced a noisy expert model and a novel variant of on-policy distillation (OPD) to address the gap between offline and online imitation learning.

result Online interaction with a noisy expert via OPD enables polynomial dependence on the horizon, unlike offline methods which require exponential growth in sample complexity.

Imitation Learning On-Policy Distillation Noisy Expert Feedback Language Model Training Sequential Decision-Making

2026-06-29abs ↗pdf ↗

Robot See, Robot Do: Imitation Reward for Noisy Financial Environmentscs.LG

Paper introduces a novel reward function for noisy financial markets using imitation learning.

problem Noisy reward function in financial markets hinders RL agent performance.

method Integrates imitation learning feedback with reinforcement learning to improve reward function design.

result Improves financial performance metrics compared to traditional benchmarks and RL agents.

reinforcement learning financial markets imitation learning reward function noisy signals

2024-11-13abs ↗pdf ↗

Expert-Aided Causal Discovery of Ancestral Graphscs.LG

AGFN improves causal discovery by integrating expert feedback and handling latent confounding.

problem Inaccurate causal discovery due to unreliable expert knowledge and latent confounding.

method Ancestral GFlowNet (AGFN) is a reinforcement learning algorithm that iteratively refines a policy based on noisy expert feedback to infer ancestral graphs.

result AGFN converges to the true ancestral graph given accurate expert responses and outperforms baselines in structural Hamming distance and Bayesian Information Criterion.

causal discovery ancestral graphs reinforcement learning expert feedback latent confounding

2023-09-21abs ↗pdf ↗

ExpertNet: Adversarial Learning and Recovery Against Noisy Labelscs.LG

ExpertNet uses noisy labels to improve deep learning robustness.

problem Improving deep learning robustness against noisy labels.

method ExpertNet framework combining Amateur and Expert models, iteratively learning from noisy labels and images.

result ExpertNet achieves robust classification with as little as 20-50% training data, outperforming state-of-the-art models.

deep learning noisy labels adversarial learning image classification robustness

2020-07-10abs ↗pdf ↗

Experts with Lower-Bounded Loss Feedback: A Unifying Frameworkcs.LG

Unified framework for expert selection with bandit and lower-bound feedback.

problem Selecting the best expert in scenarios with bandit feedback and lower-bound information.

method Introduces a new feedback model combining bandit and lower-bound information, proving optimal regret bounds for modified Exp3 algorithms.

result Optimal regret bounds for modified Exp3 algorithms, generalizing both bandit and full-information settings.

expert selection bandit feedback lower-bound information regret bounds Exp3 algorithms

2020-12-17abs ↗pdf ↗

Environment Shaping in Reinforcement Learning using State Abstractioncs.LG

A new method shapes reinforcement learning environments by abstracting large state spaces.

problem Learning in large, noisy environments with sparse feedback.

method Environment shaping using state abstraction.

result Agent's policy in shaped environment preserves near-optimal behavior in original environment.

reinforcement learning environment shaping state abstraction sparse feedback noisy signals

2020-06-23abs ↗pdf ↗

Online Learning with Uncertain Feedback Graphscs.LG

Novel algorithms for online learning with uncertain feedback graphs reduce regret.

problem Uncertainty in feedback graphs hinders traditional online learning approaches.

method Developed novel online learning algorithms to handle uncertain feedback graphs.

result Proved sublinear regret under mild conditions for the proposed algorithms.

online learning uncertain feedback regret minimization graph theory

2021-06-15abs ↗pdf ↗

Second Order Regret Bounds Against Generalized Expert Sequences under Partial Bandit Feedbackcs.LG

New algorithm minimizes expert selection regret in partial bandit feedback.

problem Minimizing expert selection regret in partial bandit feedback.

method Develops a sequential minimax optimal algorithm for a generalized partial monitoring setting.

result Second order regret bounds against a general expert selection sequence.

regret bounds partial bandit feedback sequential minimax generalized expert sequences partial monitoring

2022-04-13abs ↗pdf ↗

Improved Regret Bounds for Bandits with Expert Advicecs.LG

Improved regret bounds for bandits with expert advice.

problem Optimizing decision-making in environments with expert advice.

method Proved lower and upper bounds for regret in restricted and standard feedback models.

result Proved a new upper bound of order

\sqrt{K T \ln(N/K)}

for the worst-case regret, matching a previously known lower bound.

regret bounds bandits expert advice feedback models lower bounds

2024-06-24abs ↗pdf ↗

Learning Multiclass Classifier Under Noisy Bandit Feedbackcs.LG

Paper tackles noisy bandit feedback for multiclass classification.

problem Learning multiclass classifier with corrupted feedback.

method Proposes an unbiased estimator technique to estimate noise rates and an end-to-end framework.

result Algorithm achieves mistake bounds of

O(\sqrt{T})

in high noise and

O(T^{ icefrac{2}{3}})

in worst case.

multiclass classification noisy bandit feedback unbiased estimator noise rates mistake bound

2020-06-05abs ↗pdf ↗

Adaptive Hedging under Delayed Feedbackcs.LG

The article is devoted to investigating the application of hedging strategies to online expert weight allocation under delayed feedback. As the main result, we develop the General Hedging algorithm $\mathcal{G}$ based on the exponential reweighing of experts' losses. We build the artificial probabilistic framework and …

2019-02-27abs ↗pdf ↗

Making Efficient Use of a Domain Expert's Time in Relation Extractioncs.LG

Scarcity of labeled data is one of the most frequent problems faced in machine learning. This is particularly true in relation extraction in text mining, where large corpora of texts exists in many application domains, while labeling of text data requires an expert to invest much time to read the documents. Overall, st…

2018-07-12abs ↗pdf ↗

Improving drug sensitivity predictions in precision medicine through active expert knowledge elicitationcs.AI

Predicting the efficacy of a drug for a given individual, using high-dimensional genomic measurements, is at the core of precision medicine. However, identifying features on which to base the predictions remains a challenge, especially when the sample size is small. Incorporating expert knowledge offers a promising alt…

2017-05-09abs ↗pdf ↗

Active Imitation Learning with Noisy Guidancecs.LG

LEAQI learns to query an expert less often for noisy guidance.

problem Active imitation learning with noisy guidance to reduce expert query complexity.

method Developed LEAQI, a difference classifier that predicts expert disagreement with noisy heuristic.

result Significantly fewer queries to the expert with comparable or better accuracy.

active learning imitation learning noisy guidance sequence labeling query complexity

2020-05-26abs ↗pdf ↗

Variational Proximal Policy Optimizationstat.ML

Variational Proximal Policy Optimization improves reinforcement learning from human feedback.

problem Policy mode collapse and brittle exploration loops in reinforcement learning.

method Particle-based variational inference framework with Mixture-of-Experts architecture.

result Significant improvements in complex reasoning benchmarks.

Reinforcement Learning Human Feedback Policy Optimization Codeforces AIME

2026-06-06abs ↗pdf ↗

Optimal Investment with Costly Expert Opinionsq-fin.PM

Optimal investment strategy with expert opinions in uncertain conditions.

problem Optimizing wealth in a model with unobservable drift and costly expert opinions.

method Embedding into a full information problem, using viscosity solutions and stochastic Perron's method.

result Constructing optimal trading and expert opinion strategies under sufficient regularity conditions.

Optimal investment Markov-modulated drift Costly expert opinions Viscosity solutions Stochastic Perron's method

2024-09-17abs ↗pdf ↗

Improved Algorithms for Bandit with Graph Feedback via Regret Decompositioncs.LG

New algorithm improves bandit with graph feedback by decomposing regret.

problem Improving performance in bandit problems with graph feedback.

method Partition-based algorithm framework using regret decomposition.

result Improved and optimal regret bounds on various graph families.

bandit problem graph feedback regret decomposition interpolation expert advice

2022-05-30abs ↗pdf ↗

Online Learning-to-Defer with Varying Expertsstat.ML

Online L2D algorithm for multiclass classification with varying experts.

problem Handling streaming data, changing expert availability, and shifting expert distribution.

method First online L2D algorithm with

O((n+n_e)T^{2/3})

and

O((n+n_e)\sqrt{T})

regret guarantees.

result Effective extension of standard L2D to settings with varying expert availability and reliability.

Learning-to-Defer Online Learning Varying Experts Bandit Feedback Multiclass Classification

2026-05-12abs ↗pdf ↗

Learning Lipschitz Feedback Policies from Expert Demonstrations: Closed-Loop Guarantees, Generalization and Robustnesscs.LG

Framework learns robust control policies from expert demonstrations.

problem Adversarial robustness and closed-loop generalization in feedback control policies.

method Lipschitz-constrained loss minimization for certified robustness and generalization.

result Finite sample bound on policy learning error and robust closed-loop stability.

feedback control robustness Lipschitz closed-loop adversarial

2021-03-30abs ↗pdf ↗

Active Ranking of Experts Based on their Performances in Many Tasksstat.ML

The paper ranks experts based on task performance with noisy evaluations.

problem Ranking experts based on their performance across multiple tasks with noisy evaluations.

method Develops adaptive strategies for ranking experts with a bound on the number of queries.

result Proves strategies allowing to recover the correct ranking of experts with high probability.

expert ranking sequential learning noisy evaluations adaptive algorithms

2023-06-05abs ↗pdf ↗

Bandit optimisation of functions in the Matérn kernel RKHScs.LG

New algorithm optimizes functions in Matérn kernel RKHS with noisy feedback.

problem Optimizing functions in RKHS of Matérn kernel with noisy bandit feedback.

method π-GP-UCB algorithm with guaranteed sublinear regret for all ν > 1 and d ≥ 1.

result First practical approach with guaranteed sublinear regret for all ν > 1 and d ≥ 1.

bandit optimization Matérn kernel reproducing kernel Hilbert space sublinear regret noisy feedback

2020-01-28abs ↗pdf ↗

CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedbackcs.LG

CNT leverages noisy targets to guide model learning.

problem Learning from noisy or incomplete labels.

method Conditioning model on noisy targets at inference time.

result Model focuses on simpler sub-problems and learns from easier examples first.

supervised learning top-down feedback noisy targets imitation learning classification

2022-10-18abs ↗pdf ↗

Reinforcement Learning with Supervision from Noisy Demonstrationscs.LG

Novel framework learns policies from noisy expert demonstrations.

problem Learning effective policies with noisy expert demonstrations.

method Adaptive learning framework that jointly interacts with the environment and expert demonstrations, assigning weights to filter out noisy demonstrations.

result The proposed approach learns robustly with noisy demonstrations and achieves higher performance in fewer iterations.

Reinforcement Learning Expert Demonstrations Noisy Data Adaptive Learning Robust Policy

2020-06-14abs ↗pdf ↗

Procrastinated Tree Search: Black-box Optimization with Delayed, Noisy, and Multi-Fidelity Feedbackcs.LG

PCTS optimizes noisy, delayed, multi-fidelity feedbacks in black-box optimization.

problem Optimizing unknown functions with noisy, delayed, and multi-fidelity feedbacks.

method ProCrastinated Tree Search (PCTS) with DUCB1 and DUCBV algorithms.

result PCTS achieves better regret bounds for delayed, noisy, and multi-fidelity feedbacks.

black-box optimization delayed feedback multi-fidelity optimistic tree search UCB algorithms

2021-10-14abs ↗pdf ↗

Anomaly detection with superexperts under delayed feedbackstat.ML

New approach detects cyber-attacks in real-time.

problem Real-time detection of cyber-attacks for effective mitigation.

method Aggregates unsupervised anomaly detection algorithms and incorporates delayed feedback.

result Improves anomaly detection performance through theoretical guarantees.

cyber-attacks anomaly detection feedback superexperts real-time

2020-10-08abs ↗pdf ↗

Bayesian Online Learning for Consensus Predictioncs.LG

Bayesian framework for online consensus prediction from expert feedback.

problem Online classification with expert consensus prediction, cost-effective.

method General Bayesian framework for dynamic expert consensus estimation.

result Demonstrated superior performance on large-scale crowdsourced datasets.

Bayesian learning online classification consensus prediction crowdsourcing cost-effective

2023-12-12abs ↗pdf ↗

Sampler Design for Implicit Feedback Data by Noisy-label Robust Learningcs.IR

Adaptive sampler improves recommendation for implicit feedback data.

problem Challenges in predicting user preferences from implicit feedback data.

method Noisy-label robust learning for adaptive sampler design.

result Significant improvement in recommendation quality on real-world datasets.

recommendation implicit feedback Bayesian Point-wise Optimization Matrix Factorization Noisy-label Robust BPO

2020-06-28abs ↗pdf ↗

Bayesian Optimization for Building Social-Influence-Free Consensuscs.MA

SBO uses dual voting to build consensus in noisy feedback settings.

problem Collective decision-making under social influence.

method Dual voting system with noisy public votes and private interviews.

result Efficient consensus-building through noisy public votes, debiased by estimated social graph.

Bayesian Optimization Consensus Building Social Influence Collective Decision-Making Dual Voting

2025-02-11abs ↗pdf ↗

Online Learning Using Only Peer Predictioncs.LG

This paper considers a variant of the classical online learning problem with expert predictions. Our model's differences and challenges are due to lacking any direct feedback on the loss each expert incurs at each time step $t$ . We propose an approach that uses peer prediction and identify conditions where it succeeds.…

2019-10-10abs ↗pdf ↗

Constant regret for sequence prediction with limited advicemath.ST

Improved cumulative regret for sequence prediction with limited expert advice.

problem Minimizing cumulative regret in sequence prediction with limited information.

method Convex combination of experts with limited observation, achieving constant regret.

result Strategies achieve constant regret independent of the horizon T, improving over standard bounds.

sequence prediction cumulative regret limited advice exp-concave multi-armed bandits

2022-10-05abs ↗pdf ↗

A Probabilistic Approach for Model Alignment with Human Comparisonscs.LG

Enhances AI models with human feedback for noisy data.

problem Improving AI model alignment with human feedback in noisy environments.

method Two-stage SL+LHF framework connecting machine learning with human feedback.

result The LNCA ratio identifies conditions for SL+LHF superiority over pure SL.

human feedback model alignment label-noise comparison accuracy noisy data

2024-03-16abs ↗pdf ↗

Expertise-based Weighting for Regression Models with Noisy Labelsstat.ML

A new method combines experts' opinions to train regression models with noisy labels.

problem Training regression models with noisy labels from multiple experts.

method Estimate each labeler's expertise and combine opinions using learned weights.

result Empirically outperforms existing techniques on simulated and real data.

regression models noisy labels expert opinions machine learning flexible approach

2023-05-12abs ↗pdf ↗

Scalable Valuation of Human Feedback through Provably Robust Model Alignmentcs.LG

Hölder-DPO aligns models robustly with noisy human feedback.

problem No existing alignment methods can handle severe label noise.

method Proposes Hölder-DPO, a principled alignment loss with provable redescending property.

result Hölder-DPO enables scalable human feedback valuation and improves model alignment.

model alignment human feedback redescending property noise robustness dataset valuation

2025-05-23abs ↗pdf ↗

A Resilience Framework for Bi-Criteria Combinatorial Optimization with Bandit Feedbackcs.LG

New framework for resilient bi-criteria optimization under noisy feedback.

problem Bi-criteria combinatorial optimization with noisy function evaluations.

method Introducing

(α,β,δ, exttt{N})

-resilience and developing a black-box framework.

result Achieves sublinear regret and constraint violation for bi-criteria bandit problems.

resilience bi-criteria combinatorial optimization bandit feedback offline-to-online

2025-03-15abs ↗pdf ↗

Tracking Slowly Moving Clairvoyant: Optimal Dynamic Regret of Online Learning with True and Noisy Gradientcs.LG

This work focuses on dynamic regret of online convex optimization that compares the performance of online learning to a clairvoyant who knows the sequence of loss functions in advance and hence selects the minimizer of the loss function at each step. By assuming that the clairvoyant moves slowly (i.e., the minimizers c…

2016-05-16abs ↗pdf ↗

Towards Model-informed Precision Dosing with Expert-in-the-loop Machine Learningstat.AP

A human-in-the-loop ML framework for precision dosing reduces expert workload and removes bias.

problem High cost of data annotation and lack of appropriate data for ML models.

method Incorporates human experts into the model learning loop to improve interpretability and reduce bias.

result The approach learns interpretable rules from data and potentially lowers expert workload.

Machine Learning Precision Dosing Human-in-the-Loop Interpretability Bias Removal

2021-06-28abs ↗pdf ↗

Cooperative Online Learning with Feedback Graphscs.LG

Study how communication and feedback graphs affect learning outcomes.

problem Understanding the impact of feedback graphs on cooperative online learning.

method Analyzed network regret in terms of the independence number of the strong product of communication and feedback graphs.

result Proved bounds for network regret and demonstrated the non-improvable nature of positive results in pathological cases.

cooperative learning online learning feedback graphs regret analysis network topology

2021-06-09abs ↗pdf ↗

Online learning with noisy side observationscs.LG

New algorithm for online learning with noisy side observations.

problem Online learning with noisy side feedback and graph-structured dependencies.

method Proposes an algorithm using a weighted directed graph to model dependencies and guarantees a regret bound of O(√α* T).

result Guarantees a regret of O(√α* T) after T rounds, where α* is the effective independence number.

online learning partial observability regret minimization graph model noisy feedback

2026-04-15abs ↗pdf ↗

Online Decision Mediationstat.ML

An assistant learns to mediate decisions between humans and experts, balancing risk and learning.

problem Learning to mediate decisions between imperfect humans and expert knowledge.

method Formalizes online decision mediation, proposes a policy to balance immediate loss and future generalization.

result Consistent gains over benchmarks in decision-making performance.

decision mediation online learning bandit algorithms abstentive feedback clinical diagnosis

2023-10-28abs ↗pdf ↗

Learning Fair Division from Bandit Feedbackcs.LG

Algorithm learns fair division from noisy feedback in uncertain markets.

problem Learning fair division in uncertain markets with noisy feedback.

method Wrapper algorithms using dual averaging to learn item and agent values from bandit feedback.

result Asymptotically achieves optimal Nash social welfare in linear Fisher markets.

fair division online learning bandit feedback Nash social welfare Fisher markets

2023-11-15abs ↗pdf ↗

Beyond DAGs: Modeling Causal Feedback with Fuzzy Cognitive Mapscs.AI

Fuzzy cognitive maps (FCMs) model feedback causal relations in interwoven webs of causality and policy variables. FCMs are fuzzy signed directed graphs that allow degrees of causal influence and event occurrence. Such causal models can simulate a wide range of policy scenarios and decision processes. Their directed loo…

2019-06-26abs ↗pdf ↗

Adversarial Online Learning with noisecs.LG

We present and study models of adversarial online learning where the feedback observed by the learner is noisy, and the feedback is either full information feedback or bandit feedback. Specifically, we consider binary losses xored with the noise, which is a Bernoulli random variable. We consider both a constant noise r…

2018-10-22abs ↗pdf ↗

Active Classification with Uncertainty Comparison Queriescs.LG

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.

active learning classification uncertainty comparison oracle noisy feedback

2020-08-03abs ↗pdf ↗

(Im)possibility of Automated Hallucination Detection in Large Language Modelscs.LG

Work shows hallucination detection by LLMs is impossible without expert feedback.

problem Detecting hallucinations in LLMs is theoretically impossible without expert-labeled feedback.

method Investigated hallucination detection using a theoretical framework inspired by language identification.

result Automated hallucination detection is impossible for most language collections without expert-labeled feedback.

hallucination detection large language models language identification feedback reinforcement learning

2025-04-23abs ↗pdf ↗

A Multi-Objective Anytime Rule Mining System to Ease Iterative Feedback from Domain Expertscs.LG

Data extracted from software repositories is used intensively in Software Engineering research, for example, to predict defects in source code. In our research in this area, with data from open source projects as well as an industrial partner, we noticed several shortcomings of conventional data mining approaches for c…

2018-12-23abs ↗pdf ↗

Delayed Feedback in Kernel Banditsstat.ML

New algorithm optimizes noisy function evaluations with delayed feedback.

problem Optimizing unknown functions from noisy, delayed feedback.

method Kernel bandit problem with stochastically delayed feedback.

result Proposes an algorithm with improved regret bound for non-smooth kernels.

kernel bandits delayed feedback stochastic optimization regret bound Bayesian optimization

2023-02-01abs ↗pdf ↗

Online Dense Subgraph Discovery via Blurred-Graph Feedbackcs.LG

Paper tackles dense subgraph discovery with noisy feedback.

problem Discover dense subgraphs in edge-weighted graphs with noisy feedback.

method Proposes polynomial-time and scalable algorithms for dense subgraph discovery.

result Polynomial-time algorithm obtains nearly-optimal solution with high probability.

dense subgraph graph mining noisy feedback polynomial-time algorithm scalable algorithm

2020-06-24abs ↗pdf ↗