arXiv research

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

Improves accuracy and fairness in prediction systems with multiple domain experts.

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

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,…

Bayesian Experience Reuse improves learning from multiple experts.

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

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

In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME). Our method is inspired by the observation that networks traine…

In this work, we propose a generalized product of experts (gPoE) framework for combining the predictions of multiple probabilistic models. We identify four desirable properties that are important for scalability, expressiveness and robustness, when learning and inferring with a combination of multiple models. Through a…

Budgeted deferral framework reduces expert query costs in machine learning.

Improved algorithm reduces regret in corrupted expert advice setting.

Mixtures of experts probabilistically divide the input space into regions, where the assumptions of each expert, or conditional model, need only hold locally. Combined with Gaussian process (GP) experts, this results in a powerful and highly flexible model. We focus on alternative mixtures of GP experts, which model th…

fMRI semantic category understanding using linguistic encoding models attempt to learn a forward mapping that relates stimuli to the corresponding brain activation. Classical encoding models use linear multi-variate methods to predict the brain activation (all voxels) given the stimulus. However, these methods essentia…

New method estimates causal effects of multiple versions of treatment.

Multi-expert L2D underfits more severely, requiring new methods.

VAEs struggle with surjective multimodal data, especially class labels describing images.

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…

MAPS and MAPS-SE learn from multiple suboptimal experts to improve policies efficiently.

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

New method calibrates Gaussian product experts for better predictions.

New algorithm reduces expert prediction regret for two experts.

A new method uses a product of experts with Dirichlet variables to approximate complex distributions.

Bayesian model fuses multiple classifiers with explicit correlation modeling.

Bayesian models combine experts with a flexible gating mechanism for complex data.

Logistic regression can handle noisy labels effectively when labels are imperfectly assigned by multiple experts.

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…

In this paper, we propose a hierarchical feature-aware tracking framework for efficient visual tracking. Recent years, ensembled trackers which combine multiple component trackers have achieved impressive performance. In ensembled trackers, the decision of results is usually a post-event process, i.e., tracking result …

ICIL learns policies invariant to multiple environments, improving generalization.

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…

fMRI semantic category understanding using linguistic encoding models attempts to learn a forward mapping that relates stimuli to the corresponding brain activation. State-of-the-art encoding models use a single global model (linear or non-linear) to predict brain activation given the stimulus. However, the critical as…

We investigate the adversarial bandit problem with multiple plays under semi-bandit feedback. We introduce a highly efficient algorithm that asymptotically achieves the performance of the best switching $m$-arm strategy with minimax optimal regret bounds. To construct our algorithm, we introduce a new expert advice alg…

EBBS integrates expert assessments into MIO best-subsets problem.

Transformer models show robustness across domains with domain adversarial training.

Investigates least squares estimation in deterministic MoE models.

The paper analyzes convergence rates of softmax gating in MoE models.

TAME learns new tasks without knowing them, outperforming existing methods.

We consider the forecast aggregation problem in repeated settings, where the forecasts are done on a binary event. At each period multiple experts provide forecasts about an event. The goal of the aggregator is to aggregate those forecasts into a subjective accurate forecast. We assume that experts are Bayesian; namely…

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

Active learning method for ABC statistics selection reduces expert work and improves posterior estimates.

Bayesian framework for online consensus prediction from expert feedback.

Automated detection of MS lesions improves to 67% with 7T MRI.

A new method for sparse Gaussian process regression using correlated experts.

New method learns multiple reward functions for complex tasks.

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 …

CoCoAFusE fuses expert predictions to model complex patterns with interpretability and uncertainty.

New algorithm tackles dynamic query routing to multiple embedding models.

Prediction in a small-sized sample with a large number of covariates, the "small n, large p" problem, is challenging. This setting is encountered in multiple applications, such as precision medicine, where obtaining additional samples can be extremely costly or even impossible, and extensive research effort has recentl…

This work improves transferability of rewards inferred from expert demonstrations.