HS-MoE selects sparse experts using adaptive priors and data-adaptive gating.
problem Sparse expert selection in mixture-of-experts architectures.
method Combines horseshoe prior with input-dependent gating for data-adaptive sparsity.
result Data-adaptive sparsity in expert usage.
Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture of sparse experts to efficiently retrieve top-k classes. Different from most…
A fast method combines deep mixtures of sparse GPs for flexible modeling.
problem Flexible modeling with changing output densities.
method Designing gating network with DNN for selecting sparse GPs, using CCR algorithm.
result The method outperforms competing methods in accuracy and uncertainty quantification.
New insights into the top-K sparse softmax gating function for deep learning.
problem Understanding the theoretical effects of the top-K sparse softmax gating function on density and parameter estimations.
method Using a Gaussian mixture of experts, novel loss functions, and theoretical analysis.
result The convergence rates of density and parameter estimations are parametric under certain conditions, but slow under over-specified models.
NAMEx merges experts using Nash bargaining for improved performance.
problem Sparse Mixture of Experts merging strategies lack a principled weighting mechanism.
method Reinterpreting expert merging through game theory, introducing Nash Merging and complex momentum.
result NAMEx consistently outperforms competing methods across various tasks and system sizes.
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.
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.
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.
New method uses temperature to control sparse MoE convergence rates.
problem Sparse MoE convergence rates are slow due to temperature interactions.
method Proposes a novel activation gate to improve convergence rates.
result Improved convergence rates to polynomial rates via novel gate.
Paper analyzes approximation and learning of MoEs with (P)ReLU activation.
problem Scaling up deep learning models with MoEs and (P)ReLU activation.
method Approximation and learning-theoretic analysis of MoMLPs with (P)ReLU.
result MoMLPs can uniformly approximate Lipschitz functions with ε accuracy using O(ε−1) parameters. Mixtures-of-Experts (MoE) are conditional mixture models that have shown their performance in modeling heterogeneity in data in many statistical learning approaches for prediction, including regression and classification, as well as for clustering. Their estimation in high-dimensional problems is still however challeng…
Integrates momentum into SMoE for improved stability and robustness.
problem Stable training and robustness to data contamination in SMoE models.
method Established a connection between SMoE dynamics and gradient descent, then integrated momentum.
result MomentumSMoE is more stable and robust than SMoE.
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.
Hydra boosts efficiency for long-context reasoning in resource-constrained settings.
problem Quadratic complexity of transformers limits long-context reasoning in resource-constrained systems.
method Hydra uses a modular architecture with adaptive routing between sparse global attention, mixture-of-experts, and dual memories.
result Hydra achieves significant throughput and accuracy improvements for long-context reasoning.
Mobile V-MoEs scale down ViTs for resource-constrained vision tasks.
problem Scaling down Vision Transformers for resource-constrained applications.
method Sparse Mixture-of-Experts (MoEs) applied to entire images, with a stable training procedure.
result Mobile V-MoEs achieve better performance-efficiency trade-offs than dense ViTs.
Sparse Vision MoE matches dense networks in image recognition while using less compute.
problem Scaling vision models efficiently in computer vision.
method Vision MoE (V-MoE) - a sparse version of Vision Transformer.
result V-MoE matches state-of-the-art dense networks in image recognition with half the compute.
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.
Variational Proximal Policy Optimization improves reinforcement learning from human feedback.
problem Policy mode collapse and brittle exploration loops in reinforcement learning.
method Particle-based variational inference framework with Mixture-of-Experts architecture.
result Significant improvements in complex reasoning benchmarks.
The capacity of a neural network to absorb information is limited by its number of parameters. Conditional computation, where parts of the network are active on a per-example basis, has been proposed in theory as a way of dramatically increasing model capacity without a proportional increase in computation. In practice…
Mixture of Experts (MoE) are successful models for modeling heterogeneous data in many statistical learning problems including regression, clustering and classification. Generally fitted by maximum likelihood estimation via the well-known EM algorithm, their application to high-dimensional problems is still therefore c…
We propose a practical and scalable Gaussian process model for large-scale nonlinear probabilistic regression. Our mixture-of-experts model is conceptually simple and hierarchically recombines computations for an overall approximation of a full Gaussian process. Closed-form and distributed computations allow for effici…
New approach to sparse optimal transport for matching tokens with experts.
problem Sparse matching of tokens with experts in neural networks.
method Sparsity-constrained optimal transport with cardinality constraints.
result Solves nonconvex cardinality constraints with gradient methods.
The performance of EM in learning mixtures of product distributions often depends on the initialization. This can be problematic in crowdsourcing and other applications, e.g. when a small number of 'experts' are diluted by a large number of noisy, unreliable participants. We develop a new EM algorithm that is driven by…
The study tightens risk bounds for mixtures of experts using local differential privacy.
problem Improving risk bounds for mixtures of experts.
method Imposing local differential privacy (LDP) on the gating mechanism of mixtures of experts.
result Theoretical bounds exhibit logarithmic dependence on the number of experts and tighter than existing bounds.
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 …
Mixtures-of-Experts models and their maximum likelihood estimation (MLE) via the EM algorithm have been thoroughly studied in the statistics and machine learning literature. They are subject of a growing investigation in the context of modeling with high-dimensional predictors with regularized MLE. We examine MoE with …
DeRegiME forecasts with regime structure, improving probabilistic predictions across various time series.
problem Probabilistic forecasting discards residual uncertainty, and distribution shifts are hard to capture.
method DeRegiME uses a sparse variational Gaussian process with a nonstationary regime-mixing kernel to separate latent uncertainty regimes.
result DeRegiME improves NLPD by 20.3% on average across benchmarks, with gains on CRPS and MSE.
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.
E3 combines sparse MoEs and ensembles to improve model efficiency and performance.
problem Improving model efficiency and performance in machine learning.
method Combining sparse mixture of experts and ensembles, presenting Efficient Ensemble of Experts (E3). result E3 achieves better accuracy, log-likelihood, few-shot learning, robustness, and uncertainty estimates than baselines. Moirai-MoE improves time series forecasting by automatically specializing tokens without human-defined frequency.
problem Unified training on time series data remains challenging due to heterogeneity and non-stationarity.
method Uses sparse mixture of experts (MoE) within Transformers to automatically specialize tokens for diverse time series patterns.
result Moirai-MoE outperforms existing foundation models in both in-distribution and zero-shot scenarios.
AdaEnsemble learns adaptive feature interactions for CTR prediction.
problem Learning feature interactions for CTR prediction in recommender systems and Ads ranking.
method AdaEnsemble is a Sparsely-Gated Mixture-of-Experts (SparseMoE) architecture that dynamically selects feature interaction depth.
result AdaEnsemble achieves better prediction accuracy and inference efficiency compared to state-of-the-art models.
New functional ME models for predicting heterogeneous functional data.
problem Statistical analysis of heterogeneous functional data for prediction.
method Functional Mixtures-of-Experts (FME) models with Lasso-like regularization for sparsity.
result Accurate capture of complex nonlinear relationships and clustering of heterogeneous regression data.
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.
Improved HMoE models using Laplace gating function enhance expert specialization and performance.
problem Improving performance of hierarchical mixture of experts models.
method Used Laplace gating function instead of Softmax in hierarchical mixture of experts models.
result Laplace gating function accelerates expert convergence and enhances specialization.
This work improves Gaussian process inference using mixtures of experts and nested SMC samplers.
problem High computational and memory costs of Gaussian processes.
method Mixtures of Gaussian process experts with nested SMC samplers.
result Significantly improved inference compared to importance sampling.
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.
Estimates parameters in a deviated Gaussian mixture model.
problem Testing goodness-of-fit between a known function and a mixture of experts.
method Constructs novel Voronoi-based loss functions to estimate parameters.
result Characterizes local convergence rates of parameter estimation more accurately.
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.
Proposes GPHMEs using Gaussian processes for hierarchical expert models.
problem Hierarchical mixtures of experts with complex gating functions.
method Gaussian process-gated hierarchical mixtures of experts (GPHMEs) with non-linear gating and expert functions.
result Outperforms tree-based HMEs and achieves good performance with reduced complexity.
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.
ARGUE combines expert networks for anomaly detection.
problem Anomaly detection without labeled data.
method Gated mixture-of-experts architecture combining expert networks.
result Prior knowledge about normal data distribution is valuable.
Higher granularity in MoE models boosts expressivity exponentially.
problem Expressivity of Mixture-of-Experts models with varying granularity.
method Comparing models with different numbers of active experts (granularity).
result Exponential separation in network expressivity based on granularity.
Proposes φ-balancing for more balanced expert utilization in MoE models.
problem Balanced expert utilization in MoE models to avoid bias.
method Directly targets population-level balance by minimizing a convex potential function.
result Consistently outperforms prior methods in stability and effectiveness.
Solves challenges in estimating parameters of softmax gating Gaussian mixture models.
problem Identifiability issues and complex interactions in Gaussian mixture of experts.
method Proposes novel Voronoi loss functions and establishes convergence rates of MLE.
result Connects convergence rate of MLE to a solvability problem of polynomial equations.
Sparse neural networks can match dense models on Lipschitz functions.
problem Sparse networks are more efficient but lack theoretical guarantees.
method Formal model of sparse networks, LSH-based routing function, Lipschitz function approximation.
result Sparse networks can approximate dense networks on Lipschitz functions.
Improved time series forecasting with expert loss integration.
problem Enhancing time series forecasting accuracy and efficiency.
method Adaptive Mixture-of-Experts framework with expert-specific loss integration and online learning.
result Significantly improved forecasting accuracy and computational efficiency.
A method to improve LLMs by automating the construction of a mixture of expert prompts.
problem Limitation of single instruction prompts in covering complex problem spaces.
method Divide the problem space into sub-regions, each governed by a specialized expert with both an instruction and demos. A two-phase process constructs these experts.
result Achieves an average win rate of 81% across major benchmarks.
The paper analyzes EM for Mixtures of Experts and shows its equivalence to projected Mirror Descent.
problem Training Mixtures of Experts (MoE) models.
method Rigorously analyzes Expectation Maximization (EM) for MoE models using a Mirror Descent perspective.
result Derives new convergence results and identifies conditions for local linear convergence.