arXiv research

TFPS improves time series forecasting by learning pattern-specific experts.

Paper studies binary random projections with controllable sparsity patterns for computational and accuracy advantages.

Paper develops new patterns for unique matrix completions.

Learning latent representations of nodes in graphs is an important and ubiquitous task with widespread applications such as link prediction, node classification, and graph visualization. Previous methods on graph representation learning mainly focus on static graphs, however, many real-world graphs are dynamic and evol…

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

We analyze computational limits of modern Hopfield models based on pattern norms.

TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.

A method to select important experts for Gaussian processes to balance computational efficiency and uncertainty quantification.

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…

Improved time series forecasting with expert loss integration.

HS-MoE selects sparse experts using adaptive priors and data-adaptive gating.

NAMEx merges experts using Nash bargaining for improved performance.

Expert augmentation improves hybrid model generalization.

New method calibrates Gaussian product experts for better predictions.

Meta-algorithm optimizes nonstochastic bandits with infinitely many experts.

Deep neural networks (DNNs) are known for extracting useful information from large amounts of data. However, the representations learned in DNNs are typically hard to interpret, especially in dense layers. One crucial issue of the classical DNN model such as multilayer perceptron (MLP) is that neurons in the same layer…

New algorithm reduces expert prediction regret for two experts.

The article improves prediction by aggregating Kalman recursions online.

System uses conformal prediction to help experts make accurate decisions without understanding when to trust it.

Improved regret bounds for bandits with fixed expert advice using information theory.

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

Advice-efficient prediction with expert advice (in analogy to label-efficient prediction) is a variant of prediction with expert advice game, where on each round of the game we are allowed to ask for advice of a limited number $M$ out of $N$ experts. This setting is especially interesting when asking for advice of ever…

Reinforcement learning mimics expert behavior.

Adaptive Bayesian learning aggregates experts to improve performance.

New method aggregates Gaussian experts by detecting conditional independence violations.

Improved HMoE models using Laplace gating function enhance expert specialization and performance.

We present a new approach for learning compact and intuitive distributed representations with binary encoding. Rather than summing up expert votes as in products of experts, we employ for each variable the opinion of the most reliable expert. Data points are hence explained through a partitioning of the variables into …

ARGUE combines expert networks for anomaly detection.

Online L2D algorithm for multiclass classification with varying experts.

A new method for multi-expert learning-to-defer avoids optimization issues.

Sigmoid gating is more sample efficient than softmax in mixture of experts.

YRC-Bench benchmarks AI agents learning to collaborate with experts.

Budgeted deferral framework reduces expert query costs in machine learning.

Paper improves regret bounds for distributed experts problem.

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…

The study tightens risk bounds for mixtures of experts using local differential privacy.

We consider the problem of recovering block-sparse signals whose structures are unknown \emph{a priori}. Block-sparse signals with nonzero coefficients occurring in clusters arise naturally in many practical scenarios. However, the knowledge of the block structure is usually unavailable in practice. In this paper, we d…

DeepSeekMoE improves language model efficiency with shared experts and normalized gating.

ExpCLR uses expert features to improve time-series representation learning.

Investigates fast prediction rates with limited expert advice.

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

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…

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

Non-experts have long made important contributions to machine learning (ML) by contributing training data, and recent work has shown that non-experts can also help with feature engineering by suggesting novel predictive features. However, non-experts have only contributed features to prediction tasks already posed by e…

In the framework of prediction with expert advice, we consider a recently introduced kind of regret bounds: the bounds that depend on the effective instead of nominal number of experts. In contrast to the Normal- Hedge bound, which mainly depends on the effective number of experts but also weakly depends on the nominal…

Proposes unbiased estimators for training mixture of experts models.

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…

EBBS integrates expert assessments into MIO best-subsets problem.