We consider the problem of contextual bandits with stochastic experts, which is a variation of the traditional stochastic contextual bandit with experts problem. In our problem setting, we assume access to a class of stochastic experts, where each expert is a conditional distribution over the arms given a context. We p…
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.
168,982 papers · 148 categories
Trend · papers per month
48 results for “expert problem”
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.
Solves expert prediction problem for 4 experts in finite time horizon.
problem Expert prediction problem in finite horizon with 4 experts.
method Solves nonlinear PDE, shows solution, proves Nash equilibrium and regret conjectures.
result Proves Finite vs Geometric regret conjecture for and shows comb strategies are optimal.
New algorithm reduces expert prediction regret for two experts.
problem Efficient prediction with two experts under fixed time constraints.
method Optimal algorithm based on stochastic calculus techniques.
result Achieves optimal regret of sqrt(T/2π) + O(1) with O(1) per-turn processing time.
Optimal algorithm found for anytime regret with two experts.
problem Minimizing regret in prediction with two experts when time horizon is unknown.
method Designing a minimax optimal algorithm using ideas from stochastic calculus.
result Proved the optimal regret is γ√t / 2 for all time steps t.
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 .
New method calibrates Gaussian product experts for better predictions.
problem Erratic predictions and uncalibrated uncertainty in Gaussian product experts.
method Calibration via tempered softmax and Wasserstein barycenter for predictions.
result Improved predictions with better mean and uncertainty quantification.
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.
In mixtures-of-experts (ME) model, where a number of submodels (experts) are combined, there have been two longstanding problems: (i) how many experts should be chosen, given the size of the training data? (ii) given the total number of parameters, is it better to use a few very complex experts, or is it better to comb…
A simple algorithm improves model generalization in expert advice settings.
problem Improving model generalization in expert advice settings.
method A naive aggregation algorithm for point estimations of high-dimensional nonlinear functions.
result Conditions for optimal parameter estimates through sequential mixing distribution strategies.
We study a variant of decision-theoretic online learning in which the set of experts that are available to Learner can shrink over time. This is a restricted version of the well-studied sleeping experts problem, itself a generalization of the fundamental game of prediction with expert advice. Similar to many works in t…
Study finds optimal regret bound for multi-armed bandit problem with expert advice.
problem Optimizing decision-making in a multi-armed bandit problem with expert advice.
method Proved a tight lower bound matching the upper bound of Kale (2014) for minimax expected regret.
result The minimax optimal expected regret is Θ(√(T K log (N/K))) for the problem.
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.
This paper explores how MoE layers improve deep learning performance.
problem Understanding the Mixture-of-Experts (MoE) layer in deep learning.
method Formal study of MoE layer's effectiveness and mechanism.
result MoE layer improves performance by leveraging cluster structure and non-linearity.
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.
DMLreg uses expert knowledge to improve model performance in high-dimensional settings.
problem Improving model performance in high-dimensional prediction problems.
method Learning a Mahalanobis distance metric from expert comparisons and integrating it into a regularized linear model.
result DMLreg leads to improvements in model performance when expert knowledge is relevant.
New bounds for prediction with experts using geometric stopping.
problem Online prediction with expert advice, focusing on geometric stopping.
method Potential-based framework, explicit bounds construction.
result First explicit lower and upper bounds in geometric stopping setting.
Improved regret bounds for bandits with fixed expert advice using information theory.
problem Optimizing regret in bandit problems with fixed expert distributions.
method Information-theoretic analysis and KL-divergence measures.
result First regret bounds for EXP4 that can get arbitrarily close to zero under certain conditions.
Meta-learning model divides tasks into sub-problems for efficient adaptation.
problem Training models to quickly adapt to new tasks.
method Hierarchical Expert Networks with information-theoretic partitioning and specialized experts.
result Specialized experts lead to efficient adaptation to new tasks.
A Generalized Online Algorithm for Translation and Scale Invariant Prediction with Expert Advicecs.LG
Generalized algorithm for translation and scale-invariant prediction.
problem Sequential prediction with expert advice, focusing on translation and scale invariance.
method Designing a generalized online algorithm using the universal prediction perspective to compete against a generic class of expert selection strategies.
result No preliminary knowledge of loss sequences is required; performance bounds are stable under arbitrary scalings and translations.
Improved bounds for online prediction with expert advice.
problem Online prediction with expert advice in finite-horizon games.
method Verification arguments from optimal control theory applied to PDEs to find sub- and supersolutions.
result Explicit bounds for any number of experts and horizon, improving upon previous results.
Meta-algorithm optimizes nonstochastic bandits with infinitely many experts.
problem Maximizing reward by choosing actions sequentially from a set of experts.
method Proposed a variant of Exp4.P for infinitely many experts and a meta-algorithm.
result Proved high-probability upper bound of on regret.
Combines neural networks and expert rules for concept-based learning.
problem Extending concept-based learning with machine learning models.
method Form constraints for joint probability distribution and represent feasible set as a convex polytope.
result Neural networks can be trained to satisfy expert rules without violating them.
New algorithm reduces regret in strategic prediction problem.
problem Designing an IC algorithm with sublinear regret for strategic experts.
method Developed a new algorithm WSU-UX and proved a worst-case regret bound.
result WSU-UX suffers a lower bound on regret.
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 and regret guarantees.
result Effective extension of standard L2D to settings with varying expert availability and reliability.
Add expert knowledge to resolve ambiguities in ANN models.
problem Non-unique parameter fitting in material science.
method Augment a black-box ANN model with expert knowledge at two levels.
result Expert knowledge resolves ambiguities in parameter space.
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.
CoCoAFusE fuses expert predictions to model complex patterns with interpretability and uncertainty.
problem Modeling complex patterns with interpretability and uncertainty quantification.
method Competitive/Collaborative Fusion of Experts (CoCoAFusE) that fuses expert distributions in addition to mixing.
result CoCoAFusE avoids multimodality artifacts and provides tighter credible bounds on the response variable.
Combines expert knowledge and data for efficient probability distribution inference.
problem Inferring discrete probability distributions using limited data and expert knowledge.
method A novel estimator that weights expert knowledge and empirical data.
result The proposed estimator is always more efficient than either expert or data alone.
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 for the worst-case regret, matching a previously known lower bound.
SIRL recovers reward function probability distribution from expert actions.
problem Recovering reward functions from expert demonstrations in reinforcement learning.
method Monte Carlo Expectation-Maximization (MCEM) method to estimate reward function probability distribution.
result SIRL provides a robust and transferable solution to the IRL problem.
RadGrad selects expert queries based on agent error and risk to reduce costs.
problem Mitigating covariate shift in sequential decision prediction problems.
method Selective querying based on prediction of agent error and risk.
result Improves upon existing safety-aware algorithms and matches DAgger's performance.
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.
Bayesian Experience Reuse improves learning from multiple experts.
problem Learning from multiple experts with conflicting goals.
method Bayesian neural networks with shared features to model uncertainty and derive a probability distribution over expert models.
result BERS method effectively samples demonstrations from the derived distribution to reuse them in new tasks.
In this paper we demonstrate how genetic algorithms can be used to reverse engineer an evaluation function's parameters for computer chess. Our results show that using an appropriate expert (or mentor), we can evolve a program that is on par with top tournament-playing chess programs, outperforming a two-time World Com…
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.
YRC-Bench benchmarks AI agents learning to collaborate with experts.
problem Learning to recognize when to consult an expert in novel situations.
method Validation strategy and proposer-validator decomposition.
result Insights for future AI safety research.
In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process,data from previous tasks cannot be stored and hence is not available when learning a new…
With the increasing volume of data in the world, the best approach for learning from this data is to exploit an online learning algorithm. Online ensemble methods are online algorithms which take advantage of an ensemble of classifiers to predict labels of data. Prediction with expert advice is a well-studied problem i…
New algorithms provide long-term memory guarantees for online learning.
problem Achieving long-term memory in online learning for experts and bandits.
method Reduction to typical switching regret, developing various algorithms with specific regret bounds.
result Developed algorithms with a new regret bound of .
A new framework estimates expert policy support to create a reward function for imitation learning.
problem Imitation learning from expert trajectories without reinforcement signals.
method Estimating the support of the expert policy to compute a fixed reward function.
result Comparable or better performance than state-of-the-art methods on discrete and continuous domains.
The paper tackles efficient online learning by achieving minimal regret with respect to the best expert.
problem Achieving minimal regret in online learning problems where the goal is to match the lowest regret of K experts.
method A lazy form of the online subgradient algorithm is used to achieve minimal regret in 'easy' regimes.
result Minimal regret strategies exist for some 'hard' regimes, and the algorithm retains an worst-case regret guarantee.
A method to improve LLMs by automating the construction of a mixture of expert prompts.
problem Limitation of single instruction prompts in covering complex problem spaces.
method Divide the problem space into sub-regions, each governed by a specialized expert with both an instruction and demos. A two-phase process constructs these experts.
result Achieves an average win rate of 81% across major benchmarks.
We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or as different experts trying to solve the same task. Our main contribution is to formalise the problem as statistical preference elicitation,…
Investigates fast prediction rates with limited expert advice.
problem Minimizing excess generalization error with limited expert access.
method Assumes Lipschitz and strongly convex loss, designs novel algorithms.
result Achieves fast rates of O(1/T) with optimal number of expert advices.
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.
Optimized deferral improves accuracy in imbalanced settings.
problem Imbalance in expert predictions leads to suboptimal performance in two-stage learning to defer.
method Developed novel cost-sensitive learning algorithms and margin-based loss functions tailored for expert imbalance.
result MILD algorithm shows clear improvements over baselines in image classification and LLM routing tasks.
Study optimal trading strategies with expert signals in a hidden Gaussian drift market.
problem Optimal trading strategies in a financial market with hidden Gaussian drift and expert signals.
method Transformed power utility maximization problem into full information problem using Kalman filter estimates of the drift.
result Closed-form solutions for value function and optimal trading strategy derived.