This paper tackles deferral learning with multiple experts, providing strong theoretical guarantees.
problem Optimizing input assignment to experts balancing accuracy and computational cost.
method Introducing new surrogate loss functions and efficient algorithms with strong theoretical learning guarantees.
result Realizable H H H -consistency, H H H -consistency bounds, and Bayes-consistency for deferral learning. Paper proposes consistent estimators for learning to defer decisions to experts.
problem Learning algorithms often ignore expert decision-making in practical scenarios.
method Reduction to cost sensitive learning, novel surrogate loss for consistent estimation.
result Effective approach demonstrated on various tasks, showing consistency.
Study on learning to defer to multiple experts with consistent surrogates and confidence calibration.
problem Addressing the open problems of consistent surrogates, confidence calibration, and ensembling of experts.
method Derive two consistent surrogates (softmax and OvA) and propose a conformal inference technique for choosing experts.
result The OvA-based loss does not cause mis-calibration propagation, while the softmax-based loss does.
Multi-expert L2D underfits more severely, requiring new methods.
problem Underfitting in multi-expert L2D settings.
method PiCCE (Pick the Confident and Correct Expert), a surrogate-based method.
result PiCCE effectively reduces multi-expert L2D to a single-expert-like problem, resolving underfitting.
Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.
problem Limitation of existing L2D frameworks to single-expert deferral.
method Top- k k k Learning-to-Defer framework, including adaptive Top- k ( x ) k(x) k ( x ) variant. result Superior accuracy-cost trade-offs with multi-expert deferral.
This thesis tackles learning with multi-class abstention and multi-expert deferral, improving model reliability and efficiency.
problem Improving model reliability and efficiency in large language models (LLMs) by leveraging multiple experts.
method Developed new surrogate losses and consistency guarantees for multi-class classification and regression with deferral.
result Strong consistency guarantees for surrogate losses in multi-class classification and regression with deferral.
A novel framework for regression with multiple experts, addressing challenges in infinite and continuous label spaces.
problem Challenges in regression with multiple experts due to the infinite and continuous nature of the label space.
method Introduces a novel framework for regression with deferral, analyzing both single-stage and two-stage scenarios with new surrogate loss functions.
result Proves H H H -consistency bounds for both single-stage and two-stage methods, providing stronger guarantees than Bayes consistency. Proposes a Varying-Coefficient MoE model for analyzing dynamic data.
problem Inadequate constant coefficients in MoE models for dynamic settings.
method Varying-Coefficient Mixture of Experts (VCMoE) model with varying coefficients in gating and expert models.
result Established identifiability and consistency of the VCMoE model.
Study on learning to defer with multiple experts using new surrogate losses.
problem Learning to defer with multiple experts in a machine learning context.
method Introducing a new family of surrogate losses for the multiple-expert setting, proving H H H -consistency bounds, and designing learning algorithms. result Explicit guarantees for new learning to defer algorithms based on minimization of these surrogate losses.
A new method for learning to defer decisions with expert advice improves over standard methods.
problem Learning to defer decisions with expert advice in systems where expert information can be modified after selection.
method An augmented surrogate that operates on the composite expert-advice action space, providing consistency guarantees and excess-risk bounds.
result The method improves over standard Learning-to-Defer and adapts its advice acquisition behavior to the cost regime.
The paper studies how expert opinions improve stock return predictions in a market with a hidden drift.
problem Improving stock return predictions in a market with a hidden Gaussian drift.
method Uses Kalman filter techniques to estimate the hidden drift from noisy expert opinions and stock returns.
result The Kalman filter estimates of the drift converge to the hidden drift as the frequency of expert opinions increases.
Develops a functional mix-of-experts model for multiclass classification.
problem Multiclass classification with univariate functional predictors.
method Functional mix-of-experts model with regularization and sparsity constraints.
result Regularized maximum likelihood estimation yields interpretable coefficient functions.
Unified framework for SGMoE resolves estimation and selection issues.
problem Non-identifiability, coupled differential relations, and tight coupling in softmax-Gated models.
method Unified statistical framework with Voronoi-type loss functions and dendrograms of mixing measures.
result Consistent selection of the number of experts without model sweeps, optimal parameter rates under overfitting.
Expert-driven genetic algorithms improve chess evaluation functions.
problem Creating efficient evaluation functions for complex systems.
method Using genetic algorithms with expert guidance to evolve evaluation functions.
result Evolved programs outperform top chess programs with fewer parameters.
NAMEx merges experts using Nash bargaining for improved performance.
problem Sparse Mixture of Experts merging strategies lack a principled weighting mechanism.
method Reinterpreting expert merging through game theory, introducing Nash Merging and complex momentum.
result NAMEx consistently outperforms competing methods across various tasks and system sizes.
Proposes φ φ φ -balancing for more balanced expert utilization in MoE models.
problem Balanced expert utilization in MoE models to avoid bias.
method Directly targets population-level balance by minimizing a convex potential function.
result Consistently outperforms prior methods in stability and effectiveness.
In order to improve forecasts, a decisionmaker often combines probabilities given by various sources, such as human experts and machine learning classifiers. When few training data are available, aggregation can be improved by incorporating prior knowledge about the event being forecasted and about salient properties o…
Paper improves regret bounds for distributed experts problem.
problem Minimizing loss in a distributed experts problem.
method Protocol achieving improved regret bound with minimized communication.
result Regret bound improved to R ≳ 1 T ⋅ e x t p o l y log ( n s T ) R \gtrsim \frac{1}{\sqrt{T} \cdot ext{poly}\log(nsT)} R ≳ T ⋅ e x t p o l y l o g ( n s T ) 1 . Zero-shot imitation learns to imitate tasks without expert demonstrations.
problem Learning to imitate tasks without expert supervision.
method Explore world without supervision, distill experience into goal-conditioned policy, use forward consistency loss.
result Zero-shot imitation policy can mimic expert tasks after seeing just goal demonstrations.
Expert-augmented algorithm boosts scores in Montezuma's Revenge.
problem Sparse rewards in Montezuma's Revenge.
method Expert-augmented actor-critic algorithm.
result Achieves above 27,000 points consistently, surpassing expert performance.
Unified approach to aggregating models and preferences.
problem Consistent aggregation of models and preferences.
method Formal definition and weighted averaging of models and preferences.
result All rational aggregation rules are weighted averages of highest-ranked models/experts.
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 ) O((n+n_e)T^{2/3}) O (( n + n e ) T 2/3 ) and O ( ( n + n e ) T ) O((n+n_e)\sqrt{T}) O (( n + n e ) T ) regret guarantees. result Effective extension of standard L2D to settings with varying expert availability and reliability.
The paper tackles selective labels in decision making, proposing a data augmentation approach to mitigate bias and discrimination.
problem Selective labels cause bias in decision making, making standard bias correction methods ineffective.
method Proposes a data augmentation approach to leverage expert consistency or empirically validate models under selective labels.
result Data augmentation can mitigate the bias caused by selective labels and prevent unreliable models.
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.
Framework for safe reinforcement learning using expert demonstrations.
problem Ensuring safe behavior in reinforcement learning with unknown reward functions.
method Combines expert demonstrations with optimization methods to find safe reward functions.
result Trained agent safely avoids harmful states while mimicking expert behavior.
A method merges two pretrained diffusion experts to improve image quality and likelihood.
problem Trade-off between image quality and data likelihood in diffusion models.
method Combining two pretrained diffusion experts by switching between them along the denoising trajectory.
result The merged model consistently matches or outperforms its base components, improving or preserving both likelihood and sample quality.
Bayesian framework integrates spectral deconvolution with expert reasoning for robust peak estimation.
problem Challenges in extracting meaningful peaks from noisy or complex spectra.
method Bayesian spectral deconvolution coupled with a physical-property regression layer.
result Recovery of weak peaks in poly(lactic acid) IR spectra related to degradation rates.
A new method for multi-expert learning-to-defer avoids optimization issues.
problem Optimization issues in multi-expert learning-to-defer systems.
method A decoupled surrogate with a softmax classifier head and independent sigmoid heads per expert.
result First multi-expert L2D guarantee with a constant not growing with the expert pool.
New framework uses tempered optimism to handle imperfect experts in online learning.
problem Challenges of implicit optimism in practical online learning environments.
method Introduces tempered optimism as a framework for online non-convex learning, modifies existing algorithms.
result Demonstrates tempered optimism as a fruitful paradigm for online non-convex learning.
We revisit the classical decision-theoretic problem of weighted expert voting from a statistical learning perspective. In particular, we examine the consistency (both asymptotic and finitary) of the optimal Nitzan-Paroush weighted majority and related rules. In the case of known expert competence levels, we give sharp …
EBBS integrates expert assessments into MIO best-subsets problem.
problem Identifying relevant features in statistical models.
method Expert-implied Bayesian approach using MIO.
result Reduces to classical best-subsets when experts are silent.
A new framework uses deep RL to aggregate expert advice for better portfolio management.
problem Improving portfolio management through expert advice and deep reinforcement learning.
method Convolutional networks for signal aggregation and historical price data, Proximal Policy Optimization algorithm.
result Our framework can achieve 90% of the best expert's profit on average.
Paper improves RL from imperfect demonstrations with soft expert guidance.
problem Improper and insufficient expert demonstrations in RLfD.
method Formalizes imperfect expert setting, tackles optimality and convergence issues with soft constraints, and uses local linear search on dual form.
result Method achieves consistent improvement over other RLfD methods.
We present a novel approach for supervised domain adaptation that is based upon the probabilistic framework of Gaussian processes (GPs). Specifically, we introduce domain-specific GPs as local experts for facial expression classification from face images. The adaptation of the classifier is facilitated in probabilistic…
A new method for sparse Gaussian process regression using correlated experts.
problem Sparse Gaussian process regression for large datasets with cubic computational complexity.
method Aggregating predictions from correlated experts to improve scalability and accuracy.
result Superior performance compared to state-of-the-art methods for synthetic and real-world datasets.
Conventional learning with expert advice methods assumes a learner is always receiving the outcome (e.g., class labels) of every incoming training instance at the end of each trial. In real applications, acquiring the outcome from oracle can be costly or time consuming. In this paper, we address a new problem of active…
Sharp bounds found on expert error in binary advice aggregation.
problem Aggregating binary advice from conditionally independent experts.
method Sharp upper and lower bounds on optimal error probability in asymmetric case.
result Sharp bounds recover and sharpen known results in symmetric case.
The paper proposes methods to identify and sample from mixtures of Mallows models for top-k rankings.
problem Identifying and sampling from mixtures of Mallows models for top-k rankings in a heterogeneous population.
method Efficient sampling algorithms and identifiability proofs for both components of the mixture.
result The identifiability and learnability of the Mallows components' parameters in the mixture.
Develops a simulation-based method to translate expert knowledge into prior distributions for Bayesian models.
problem Effective incorporation of expert knowledge into prior distributions for diverse model structures.
method Simulation-based stochastic gradient descent to learn hyperparameters of parametric priors from expert knowledge.
result Method is adaptable to various elicitation techniques and independent of model structure.
Paper introduces deep structured mixtures of Gaussian processes for scalable GP approximations.
problem Scalability issues with Gaussian Processes (GPs).
method Deep structured mixtures of GP experts for scalable approximate inference.
result Deep structured mixtures provide better predictive uncertainties and competitive performance.
LHM integrates expert ODEs with neural ODEs for disease progression prediction.
problem Predicting disease progression under medications using limited data.
method Integrating expert-designed ODEs with machine-learned Neural ODEs.
result LHM consistently outperforms previous methods, especially in small sample regimes.
Study improves stock price prediction using adaptive Mixture of Experts framework.
problem Tackles diverse volatility regimes in stock price prediction.
method Combines RNN for high-volatility stocks and linear regression for stable stocks with a gating mechanism.
result Achieves up to 33% improvement in MSE for volatile assets and 28% for stable assets.
FinFlowRL learns from experts to optimize financial control in changing markets.
problem Traditional finance control methods fail in real-world, non-stationary markets.
method Imitation-Reinforcement Learning framework that pretrains on expert strategies and finetunes in noise space.
result Consistently outperforms individually optimized experts across diverse market conditions.
A new model improves the performance of knowledge distillation in GNNs.
problem Inconsistent performance of existing knowledge distillation techniques in GNNs.
method Proposes a new model, Routing-by-Memory (RbM), a form of Mixture-of-Experts (MoE), to address performance concerns.
result Demonstrates experimentally that RbM achieves considerably more consistent performance across multiple datasets.
Study assesses consistency and reproducibility of LLMs in finance and accounting tasks.
problem Consistency and reproducibility of LLM outputs in finance and accounting research.
method Extensive experimentation with 50 independent runs across 5 tasks using 3 OpenAI models.
result Task-specific patterns of consistency and reproducibility, with binary classification and sentiment analysis achieving near-perfect reproducibility.
Algorithm learns expert weights to minimize regret in adversarial setting.
problem Learning to aggregate expert forecasts with no-regret guarantee in adversarial conditions.
method Online mirror descent algorithm for logarithmic pooling of expert forecasts.
result Achieves O ( T log T ) O(\sqrt{T} \log T) O ( T log T ) expected regret compared to best weights. We investigate a class of hierarchical mixtures-of-experts (HME) models where exponential family regression models with generalized linear mean functions of the form psi(ga+fx^Tfgb) are mixed. Here psi(...) is the inverse link function. Suppose the true response y follows an exponential family regression model with mea…
SARD improves adversarial robustness in two-stage L2D systems.
problem Adversarial attacks can manipulate query allocation in two-stage L2D systems.
method Introduces SARD, a convex learning algorithm with provable guarantees.
result SARD significantly improves robustness under adversarial attacks while maintaining strong clean performance.