New UCB algorithms tackle contextual bandits with stochastic experts, achieving instance-dependent regret bounds.
problem Contextual bandits with stochastic experts, a variation of traditional stochastic contextual bandits.
method Proposes UCB algorithms using importance sampling to estimate mean rewards from multiple experts.
result Achieves instance-dependent regret bounds of $\mathcal{O}\left(λ(\pmbμ)\mathcal{M}\log T/Δ
ight)$ , with λ ( μ ) λ(\pmbμ) λ ( μ ) typically O ( log N ) \mathcal{O}(\log N) O ( log N ) . 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.
Improved algorithm reduces regret in corrupted expert advice setting.
problem Prediction with expert advice in the presence of adversarial corruption.
method Multiplicative Weights algorithm with decreasing step sizes.
result Achieves constant regret and optimal performance in various environments.
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.
Proposes unbiased estimators for training mixture of experts models.
problem Efficiently training large-scale mixture of experts models on modern hardware.
method Two unbiased estimators based on principled stochastic assignment procedures.
result Both estimators are more effective and robust than biased alternatives.
We investigate online classification with paid stochastic experts. Here, before making their prediction, each expert must be paid. The amount that we pay each expert directly influences the accuracy of their prediction through some unknown Lipschitz "productivity" function. In each round, the learner must decide how mu…
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.
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.
Hedge algorithm proves optimal in stochastic expert advice problems.
problem Prediction with expert advice in stochastic setting.
method Analyzed Hedge algorithm with decreasing learning rate in online stochastic setting.
result Hedge algorithm is worst-case optimal and adaptive in stochastic setting.
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.
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.
New algorithms learn model complexity and stochasticity robustly in online prediction.
problem Learning model complexity and stochasticity in online prediction.
method Probabilistic structural risk minimization integrated into adaptive algorithms.
result Competitive regret bounds for model and stochasticity adaptivity.
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.
VMoER improves uncertainty quantification in MoE layers for scalable foundation models.
problem Uncertainty quantification in large-scale models like MoE layers.
method Structured Bayesian approach with amortized variational inference over routing logits and temperature parameter inference.
result Improves routing stability, reduces calibration error, and increases AUROC by 12%.
Improved prediction algorithm for 'easy' sequences with reduced regret.
problem Prediction with expert advice for 'easy' sequences.
method Variant of NormalHedge algorithm using second-order ε ε ε -quantile regret bound. result Second-order ε ε ε -quantile regret bound of O ( V T log ( V T / ε ) ) O\big(\sqrt{V_T \log(V_T/ε)}\big) O ( V T log ( V T / ε ) ) for V T > log N V_T > \log N V T > log N . Combines expert models using Kullback-Leibler divergence to create a combined model.
problem Combining expert views on stochastic processes.
method Minimizes weighted Kullback-Leibler divergence to create a barycentre model.
result Existence and uniqueness of the barycentre model with explicit representation.
Continuous control imitation learning fails if expert actions are smooth.
problem Continuous control imitation learning fails if expert actions are smooth.
method Study of imitation learning in discrete-time, continuous state-and-action control systems.
result Any smooth, deterministic imitator policy suffers exponentially larger error than the expert.
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.
The paper aims to reduce bias in online decision-making by optimizing fairness and regret.
problem Achieving fair and justified real-time decisions in online systems.
method Adapting the learning-from-experts scheme to optimize fairness and regret for multiple label classes and sensitive groups.
result Approximately equalized odds can be achieved without significant loss in regret.
FinFlowRL combines imitation and reinforcement learning for better financial control.
problem Traditional stochastic control methods fail in real-world finance due to changing market conditions.
method FinFlowRL uses imitation learning to pretrain an adaptive meta policy, then finetunes it with reinforcement learning.
result FinFlowRL consistently outperforms individual strategies across various market conditions.
Learning from demonstration (LfD) is the process of building behavioral models of a task from demonstrations provided by an expert. These models can be used e.g. for system control by generalizing the expert demonstrations to previously unencountered situations. Most LfD methods, however, make strong assumptions about …
Paper investigates IRL for learning expert agents' reward functions in LOB dynamics.
problem Learning expert agents' reward functions in LOB dynamics.
method Investigates IRL methods to infer reward functions from expert demonstrations in LOB environments.
result GP-based and BNN methods can discover non-linear reward functions in LOB dynamics.
MoE outperforms vanilla networks in detecting latent cluster structures in regression tasks.
problem Detecting latent cluster structures in regression tasks with gradient-based learning.
method Theoretical analysis of Mixture of Experts (MoE) using stochastic gradient descent (SGD).
result MoE can successfully divide the problem into subproblems, allowing each expert to recover simpler functions corresponding to individual clusters.
Study improves privacy-preserving online prediction from experts with speed-ups.
problem Privacy-preserving online prediction from experts with speed-ups.
method Differentially private federated online prediction algorithms.
result Achieves m m m -fold regret speed-up with low-loss expert in federated setting. This study analyzes communication constraints in MoE architectures using information theory.
problem Communication constraints in Mixture-of-Experts (MoE) architectures.
method Developed a rate-distortion characterization of finite-rate gating in MoE architectures using information theory.
result Yielded capacity-aware limits for communication-constrained MoE systems.
Paper tackles inverse reinforcement learning with non-optimal demonstrations in zero-sum games.
problem Inverse reinforcement learning with sub-optimal expert demonstrations in zero-sum games.
method Introduces a new objective function and algorithm to find reward function and strategies without decoupling agents.
result Demonstrates recovery of reward functions and strategies with good quality from sub-optimal expert demonstrations.
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.
New algorithm improves on EM for streaming data, outperforming existing methods.
problem Processing high-volume, streaming data efficiently.
method Incremental stochastic Majorization-Minimization (MM) algorithm.
result The algorithm converges to a stationary point with vanishing gradient.
GH-PID uses guided harmonic paths for efficient SOT with interpretable diagnostics.
problem Efficiently solving Stochastic Optimal Transport with hard terminal distributions and soft costs.
method Guided Harmonic Path-Integral Diffusion (GH-PID) framework with low-dimensional guidance.
result GH-PID generates geometry-aware, cost-reducing trajectories that match terminal distributions.
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.
Efficiently trains large CNN models for hashtag prediction.
problem Training large CNN models with limited GPU memory.
method Hard mixture of experts model trained in parallel.
result Large scale models trained with minimal fragmentation.
Active learning improves RS-IRL by querying expert demonstrations to uncover risk boundaries.
problem Efficient learning from expert demonstrations in risk-sensitive IRL.
method Probabilistic disturbance sampling scheme for active learning.
result Our approach accelerates RS-IRL convergence with lower variance and unbiased results.
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 O ( T ( S ln T + n ln K ) ) \mathcal{O}(\sqrt{T(S\ln T + n \ln K)}) O ( T ( S ln T + n ln K ) ) . The paper provides theoretical guarantees for behavior cloning using generative models.
problem Behavior cloning of complex expert demonstrations using generative models.
method The paper proposes a theoretical framework invoking low-level controllers to stabilize imitation around expert demonstrations. It shows that with suitable low-level stability guarantees and powerful generative models, pure supervised behavior cloning can match expert trajectories.
result The paper proves that with a suitable low-level stability guarantee and a powerful enough generative model, pure supervised behavior cloning can generate trajectories matching the per-time step distribution of essentially arbitrary expert trajectories in an optimal transport cost.
FlowOE learns from experts to optimize financial trades.
problem Optimal execution in dynamic financial markets using static models.
method Imitation learning with flow matching models, incorporating refining loss function.
result Significantly outperforms expert models and traditional benchmarks.
Paper explores limits of imitation learning in MDPs, setting new suboptimality bounds.
problem Understanding the statistical limits of imitation learning in MDPs.
method Analyzes minimax statistical limits in two settings: pre-interaction and interaction.
result Establishes suboptimality bounds for imitation learning in MDPs, showing improvements with knowledge of transition.
Study online monotone density estimation with expert aggregation and log-optimal calibration.
problem Online monotone density estimation and log-optimal calibration.
method Proposed two online estimators: Grenander estimator and expert aggregation estimator.
result Online estimators achieve O ( n 1 / 3 ) O(n^{1/3}) O ( n 1/3 ) cumulative log-likelihood gap and n log n \sqrt{n\log{n}} n log n pathwise regret bound. DSelect-k improves MoE models for multi-task learning with better performance and smoother training.
problem Smoothness and convergence issues in sparse gate selection for MoE models.
method Developed DSelect-k, a differentiable and sparse gate for MoE models.
result DSelect-k achieves statistically significant improvements in prediction and expert selection over Top-k.
Paper studies continuous prediction with experts' advice using differential equations.
problem Continuous prediction with experts' advice in online learning.
method Continuous-time stochastic calculus and differential equations.
result Improved guarantees for quantile regret with continuous-time algorithm.
A new model predicts multivariate regression using similarities to data points.
problem Complex, high-dimensional input-output relationships.
method Bayesian mixture-of-experts with conditional Gaussian mixtures and variational Bayes.
result Outperforms competitors in high-dimensional settings.
Reinforcement learning improves online matching by combining expert policies.
problem Efficient decision-making in complex systems like cloud services and marketplaces.
method Combines reinforcement learning with expert policies, using advantage-based weight updates.
result The orchestrated policy converges faster and yields higher efficiency than individual experts and conventional RL.
MoE-F combines LLMs online for better time-series prediction.
problem Combining multiple LLMs for online time-series prediction.
method Time-adaptive stochastic filtering techniques to combine experts.
result MoE-F achieves 17% absolute and 48.5% relative F1 measure improvement.
This paper investigates optimal portfolio strategies in a market where the drift is driven by an unobserved Markov chain. Information on the state of this chain is obtained from stock prices and expert opinions in the form of signals at random discrete time points. As in Frey et al. (2012), Int. J. Theor. Appl. Finance…
New technique reduces imitation learning performance gap in finite samples.
problem Imitation learning performance gap in finite samples.
method Replay estimation to reduce empirical variance in finite samples.
result Achieves optimal performance gap of $\widetilde{O} \left( \min({H^{3/2}} / {N}, {H} / {\sqrt{N}}
ight)$ .
Optimizes quantile and semi-adversarial regret with novel root-logarithmic regularizers.
problem Minimizes regret in adversarial and semi-adversarial online learning.
method FTRL with root-logarithmic regularizers for quantile and semi-adversarial settings.
result Achieves minimax optimal regret bounds in both paradigms.
We introduce a means of automating machine learning (ML) for big data tasks, by performing scalable stochastic Bayesian optimisation of ML algorithm parameters and hyper-parameters. More often than not, the critical tuning of ML algorithm parameters has relied on domain expertise from experts, along with laborious hand…
New algorithms improve online prediction from experts with privacy constraints.
problem Online prediction from experts under privacy constraints.
method Proposed and analyzed new algorithms for approximate and pure differential privacy.
result Achieved improved regret bounds for various adversaries.
The paper improves on existing algorithms for minimizing different types of regret in online learning.
problem Minimizing external, internal, and swap regret in online learning with multiple experts.
method Develops a single algorithm using φ-regret minimization and Haar-wavelet-inspired matrix features to achieve optimal bounds in various scenarios.
result Achieves optimal bounds for external, internal, and swap regrets in different expert scenarios.