Proposes a partially linear structure to capture nonlinear relationships in mixture of experts models.
problem Suboptimal estimates due to linearity assumption in mixture of experts models.
method Introduces a partially linear structure that incorporates unspecified functions to capture nonlinear relationships.
result Establishes the identifiability of the proposed model under mild conditions and introduces a practical estimation algorithm.
Study analyzes convergence of parameter estimation in contaminated mixture of experts.
problem Challenges in learning from prompts in large-scale models.
method Convergence analysis, distinguishability condition, partial differential equations.
result Comprehensive convergence rates and minimax lower bounds for parameter estimation.
Bayesian framework integrates spectral deconvolution with expert reasoning for robust peak estimation.
problem Challenges in extracting meaningful peaks from noisy or complex spectra.
method Bayesian spectral deconvolution coupled with a physical-property regression layer.
result Recovery of weak peaks in poly(lactic acid) IR spectra related to degradation rates.
MoEs can efficiently model complex tasks with low-dimensionality and sparsity.
problem Understanding the theoretical foundations of MoEs for complex tasks.
method Systematic study of MoEs with two structural priors: low-dimensionality and sparsity.
result MoEs can approximate functions on low-dimensional manifolds and exhibit exponential structured tasks.
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.
TENP prunes experts and neurons in Mixture-of-Experts models for efficient deployment.
problem Efficient deployment of large language models constrained by static parameter footprint.
method Structured Trapezoidal ExpertNeuron Pruning (TENP) identifies and retains important experts and neurons.
result DeepSeek model achieves 10% better performance on code generation tasks with 40% expert sparsity.
Gaussian Processes (GPs) are powerful non-parametric Bayesian regression models that allow exact posterior inference, but exhibit high computational and memory costs. In order to improve scalability of GPs, approximate posterior inference is frequently employed, where a prominent class of approximation techniques is ba…
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…
Competency questions help experts select best clustering for energy data.
problem Ad hoc and subjective selection of clustering structures by domain experts.
method Formalize expert knowledge and requirements with competency questions.
result Competency questions improve reproducibility and evaluation of clustering applications.
In regression tasks the distribution of the data is often too complex to be fitted by a single model. In contrast, partition-based models are developed where data is divided and fitted by local models. These models partition the input space and do not leverage the input-output dependency of multimodal-distributed data,…
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.
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 i l d e O ( i ∗ K + K T ) ilde{\mathcal{O}} \big( i^*K + \sqrt{KT} \big) i l d e O ( i ∗ K + K T ) on regret. Bayesian models combine experts with a flexible gating mechanism for complex data.
problem Theoretical properties of Bayesian mixture-of-experts models with softmax gating remain unexplored.
method Investigated asymptotic behavior of posterior distribution for density estimation, parameter estimation, and model selection.
result Established posterior contraction rates for density estimation and parameter estimation, providing insights for practical model design.
Dual-structured method improves cross-domain imitation learning.
problem Learning policies in a target domain from source domain expert demonstrations.
method Extracts domain and policy expertness features, synthesizes new features.
result Superior performance compared to other algorithms in MuJoCo tasks.
The paper proposes a semi-parametric Bayesian network model using Gaussian Processes and Horseshoe priors.
problem Learning semi-parametric relationships in Expert Bayesian Networks with minimal nonlinear components.
method Uses Gaussian Processes and Horseshoe priors to model relationships, prioritizes modifying expert graphs, and generates diverse graphs.
result Models outperform state-of-the-art semi-parametric Bayesian Network models in synthetic and real-world datasets.
DeepSeekMoE improves language model efficiency with shared experts and normalized gating.
problem Improving sample efficiency in language model architectures.
method Theoretical and empirical analysis of shared experts and normalized sigmoid gating.
result Theoretical and empirical evidence of improved sample efficiency with shared experts and normalized gating.
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.
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…
The paper develops a method for inferring second opinions from experts using counterfactual inference.
problem Designing efficient decision support systems for second opinions.
method Set invariant Gumbel-Max structural causal model for multiclass classification.
result The proposed model can infer second opinions more accurately than non-causal models.
A method merges two pretrained diffusion experts to improve image quality and likelihood.
problem Trade-off between image quality and data likelihood in diffusion models.
method Combining two pretrained diffusion experts by switching between them along the denoising trajectory.
result The merged model consistently matches or outperforms its base components, improving or preserving both likelihood and sample quality.
With super-resolution optical microscopy, it is now possible to observe molecular interactions in living cells. The obtained images have a very high spatial precision but their overall quality can vary a lot depending on the structure of interest and the imaging parameters. Moreover, evaluating this quality is often di…
Sigmoid gating is more sample efficient than softmax in mixture of experts.
problem Softmax gating leads to unnecessary competition among experts, causing representation collapse.
method Theoretical analysis of a regression framework with mixture of experts, identifying identifiability conditions and convergence rates.
result Sigmoid gating requires fewer samples to achieve the same expert estimation error as softmax gating.
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…
New model handles complex non-linear relationships with hidden graph structures.
problem Modeling non-linear relationships with hidden graph-structured interactions.
method Block-diagonal localized mixture of polynomial experts (BLoMPE) regression model with penalized maximum likelihood selection criterion.
result Strong theoretical guarantee for finite-sample oracle inequality.
The paper analyzes convergence rates of softmax gating in MoE models.
problem The effectiveness and scalability of machine learning models using MoE.
method Convergence analysis of parameter and expert estimation under MoE with softmax gating and its variants.
result Theoretical results show polynomially many data points are needed for strong identifiability conditions, while exponential points are required for linear experts.
Improved transfer learning with expert models, reducing compute and speeding up performance.
problem Improving sample efficiency and reducing computational requirements for new tasks.
method Training a diverse set of experts using existing label structures and performance proxies to select the relevant expert for each target task.
result Significant speed-up of 2-3 orders of magnitude compared to competing approaches.
New algorithm tackles dynamic query routing to multiple embedding models.
problem Dynamic query routing to multiple embedding models under adversarial conditions.
method Formalized as adversarial contextual linear bandit with low-rank experts, proposed HPG algorithm.
result HPG algorithm achieves linearized policy regret of i l d e O ( s M T ) ilde{\mathcal O}(s\sqrt{M T}) i l d e O ( s M T ) . AGFN improves causal discovery by integrating expert feedback and handling latent confounding.
problem Inaccurate causal discovery due to unreliable expert knowledge and latent confounding.
method Ancestral GFlowNet (AGFN) is a reinforcement learning algorithm that iteratively refines a policy based on noisy expert feedback to infer ancestral graphs.
result AGFN converges to the true ancestral graph given accurate expert responses and outperforms baselines in structural Hamming distance and Bayesian Information Criterion.
LEAQI learns to query an expert less often for noisy guidance.
problem Active imitation learning with noisy guidance to reduce expert query complexity.
method Developed LEAQI, a difference classifier that predicts expert disagreement with noisy heuristic.
result Significantly fewer queries to the expert with comparable or better accuracy.
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.
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,…
Unified framework for expert selection with bandit and lower-bound feedback.
problem Selecting the best expert in scenarios with bandit feedback and lower-bound information.
method Introduces a new feedback model combining bandit and lower-bound information, proving optimal regret bounds for modified Exp3 algorithms.
result Optimal regret bounds for modified Exp3 algorithms, generalizing both bandit and full-information settings.
Framework uses expert intervention to solve long-horizon reinforcement learning tasks.
problem Long horizon robot learning tasks with sparse rewards.
method Option templates and expert intervention to enable high-level task understanding.
result Framework outperforms state-of-the-art approaches by two orders of magnitude.
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%.
MM-DREX adapts LLM experts for financial trading via dynamic routing.
problem Challenges of non-stationary financial markets and static expert designs.
method MM-DREX uses a VLM-powered dynamic router to allocate expert weights and designs heterogeneous trading experts.
result Significantly outperforms 15 baselines across key metrics.
A framework for faster, better infographic design by non-experts and experts alike.
problem Designing infographics is time-consuming and tedious for non-experts and even professionals.
method Semi-automated infographic framework for structured and flow-based designs, including automatic design ranking and customization options.
result Designers from all expertise levels can generate generic infographic designs faster than existing methods while maintaining quality.
Optimal policies identified for learning systems with a malicious expert.
problem Adversarial attacks on learning systems combining expert advice.
method Analysis of offline and online settings, dynamic programming for online setting.
result Greedy policy is asymptotically optimal with approximation ratio for offline setting.
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.
Paper hypothesizes MLP layers in LLMs can be approximated by sparse Mixture of Experts.
problem Understanding dense MLP layers in LLMs.
method Theoretical connection between MoE models and SAE structure in activation space.
result MLP layers in LLMs can be well approximated by sparse Mixture of Experts.
Proposes a Varying-Coefficient MoE model for analyzing dynamic data.
problem Inadequate constant coefficients in MoE models for dynamic settings.
method Varying-Coefficient Mixture of Experts (VCMoE) model with varying coefficients in gating and expert models.
result Established identifiability and consistency of the VCMoE model.
Paper proposes interpretable RL policies from a mixture of experts.
problem Making RL policies transparent and understandable in real-world applications.
method Policy iteration scheme with interpretable experts and prototypical states.
result Proposed algorithm learns policies comparable to neural networks but more interpretable.
This paper tackles model selection for MoE models in high-dimensional data.
problem Model selection for Gaussian-gated localized MoE and block-diagonal covariance localized MoE regression models in high-dimensional data.
method Penalized maximum likelihood estimation framework with non-asymptotic risk bounds.
result Established non-asymptotic risk bounds for model selection in MoE models.
Despite significant advances in artificial intelligence (AI) for computer vision, its application in medical imaging has been limited by the burden and limits of expert-generated labels. We used images from optical coherence tomography angiography (OCTA), a relatively new imaging modality that measures perfusion of the…
PRISM-VQ combines financial priors with vector quantization for better stock prediction.
problem Predicting cross-sectional stock returns is hard due to low signal-to-noise ratios and changing market conditions.
method Integrates expert priors, vector-quantized latent factors, and dynamic factor loadings.
result Consistent improvements in cross-sectional return prediction and portfolio performance.
Improved MoE performance through perturbing cosine router.
problem Representation collapse and parameter redundancy in MoE models.
method Least square estimation of cosine router in MoE, followed by noise addition to improve convergence rates.
result Perturbed cosine router leads to polynomial convergence rates for MoE models.
A method to select important experts for Gaussian processes to balance computational efficiency and uncertainty quantification.
problem Balancing computational efficiency and uncertainty quantification in Gaussian processes for big data.
method Using graphical models to select important experts and aggregate their predictions while ensuring uncertainty quantification.
result Substantially reduces computational cost of aggregating dependent experts while ensuring calibrated uncertainty quantification.
This thesis tackles learning with multi-class abstention and multi-expert deferral, improving model reliability and efficiency.
problem Improving model reliability and efficiency in large language models (LLMs) by leveraging multiple experts.
method Developed new surrogate losses and consistency guarantees for multi-class classification and regression with deferral.
result Strong consistency guarantees for surrogate losses in multi-class classification and regression with deferral.
The paper presents a novel approach to multi-output regression using probabilistic circuits.
problem Capturing correlations between multiple output dimensions in large-scale regression problems.
method Employing a mixture of single-output Gaussian process experts encoded via a probabilistic circuit.
result The method can capture correlations between output dimensions and often outperforms other approaches.