arXiv research

Improved time series forecasting with expert loss integration.

In this paper we extend the setting of the online prediction with expert advice to function-valued forecasts. At each step of the online game several experts predict a function, and the learner has to efficiently aggregate these functional forecasts into a single forecast. We adapt basic mixable (and exponentially conc…

A new CoVaR framework integrates expert views using entropy pooling.

Study on learning to defer with multiple experts using new surrogate losses.

The paper tackles online learning with two types of losses and shows it's impossible without certain assumptions.

We consider a learning system based on the conventional multiplicative weight (MW) rule that combines experts' advice to predict a sequence of true outcomes. It is assumed that one of the experts is malicious and aims to impose the maximum loss on the system. The loss of the system is naturally defined to be the aggreg…

Paper improves regret bounds for distributed experts problem.

Generalized algorithm for translation and scale-invariant prediction.

This paper tackles deferral learning with multiple experts, providing strong theoretical guarantees.

Study on learning to defer to multiple experts with consistent surrogates and confidence calibration.

New algorithm minimizes expert selection regret in partial bandit feedback.

The paper introduces a method to incorporate expert opinion on observable quantities into statistical models.

New bounds on minimax regret for sequential probability assignment using logarithmic loss.

New algorithms avoid a dominant lower-order term in heavy-tailed loss settings.

We consider prediction with expert advice under the log-loss with the goal of deriving efficient and robust algorithms. We argue that existing algorithms such as exponentiated gradient, online gradient descent and online Newton step do not adequately satisfy both requirements. Our main contribution is an analysis of th…

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

A novel framework for regression with multiple experts, addressing challenges in infinite and continuous label spaces.

Paper proposes consistent estimators for learning to defer decisions to experts.

This thesis tackles learning with multi-class abstention and multi-expert deferral, improving model reliability and efficiency.

We study online aggregation of the predictions of experts, and first show new second-order regret bounds in the standard setting, which are obtained via a version of the Prod algorithm (and also a version of the polynomially weighted average algorithm) with multiple learning rates. These bounds are in terms of excess l…

Optimized deferral improves accuracy in imbalanced settings.

We develop the setting of sequential prediction based on shifting experts and on a "smooth" version of the method of specialized experts. To aggregate experts predictions, we use the AdaHedge algorithm, which is a version of the Hedge algorithm with adaptive learning rate, and extend it by the meta-algorithm Fixed Shar…

Estimates parameters in a deviated Gaussian mixture model.

A new mechanism reduces expert belief regret in online forecasting.

Thompson Sampling, one of the oldest heuristics for solving multi-armed bandits, has recently been shown to demonstrate state-of-the-art performance. The empirical success has led to great interests in theoretical understanding of this heuristic. In this paper, we approach this problem in a way very different from exis…

Study post-hoc Learning to Defer using density-ratio losses.

Expert system predicts credit card charge-offs using macroeconomic indicators.

Gating is a key feature in modern neural networks including LSTMs, GRUs and sparsely-gated deep neural networks. The backbone of such gated networks is a mixture-of-experts layer, where several experts make regression decisions and gating controls how to weigh the decisions in an input-dependent manner. Despite having …

Algorithm learns expert weights to minimize regret in adversarial setting.

The goal of online prediction with expert advice is to find a decision strategy which will perform almost as well as the best expert in a given pool of experts, on any sequence of outcomes. This problem has been widely studied and $O(\sqrt{T})$ and $O(\log{T})$ regret bounds can be achieved for convex losses (\cite{zin…

Unified framework for SGMoE resolves estimation and selection issues.

Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.

Improved cumulative regret for sequence prediction with limited expert advice.

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 …

Bayesian framework integrates spectral deconvolution with expert reasoning for robust peak estimation.

LHM integrates expert ODEs with neural ODEs for disease progression prediction.

EBBS integrates expert assessments into MIO best-subsets problem.

Algorithm detects changes online using expert tracking.

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.…

The paper proposes using experts' insights in machine learning tasks.

PCGS-TF uses a Transformer to adaptively control expert switching in non-stationary environments.

Study examines Lasso performance in high-dimensional MoE models.

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

Proposes $φ$-balancing for more balanced expert utilization in MoE models.

Adaptive Bayesian learning aggregates experts to improve performance.

Recent research has shown that although Reinforcement Learning (RL) can benefit from expert demonstration, it usually takes considerable efforts to obtain enough demonstration. The efforts prevent training decent RL agents with expert demonstration in practice. In this work, we propose Active Reinforcement Learning wit…

Study shows training duration affects model merging quality, suggesting joint selection of duration and method.

FlowOE learns from experts to optimize financial trades.