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.
A new method for sparse Gaussian process regression using correlated experts.
problem Sparse Gaussian process regression for large datasets with cubic computational complexity.
method Aggregating predictions from correlated experts to improve scalability and accuracy.
result Superior performance compared to state-of-the-art methods for synthetic and real-world datasets.
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.
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.
Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent and an expert use different actions from each other. We assume that the agent has access to a sparse reward function and state-only expert observa…
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.
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.
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.
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.
New conditions show proxy data can improve policy learning in sparse expert data contexts.
problem Improving sample complexity of policy learning with sparse expert data.
method Sufficient conditions for proxy data to improve sample complexity, adaptable to LLMs.
result Provable improvement in sample complexity for policy learning with proxy data.
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…
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.
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.
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.
We propose an expert-augmented actor-critic algorithm, which we evaluate on two environments with sparse rewards: Montezumas Revenge and a demanding maze from the ViZDoom suite. In the case of Montezumas Revenge, an agent trained with our method achieves very good results consistently scoring above 27,000 points (in ma…
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…
Sparse routing networks with co-training prevent catastrophic forgetting in continual learning.
problem Catastrophic forgetting in neural networks trained on a sequence of tasks.
method Sparse routing networks with co-training to minimize interference between dissimilar tasks.
result Sparse routing networks with co-training outperform densely connected networks on benchmarks.
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.
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.
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.
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.
New algorithms approximate Rashomon set for sparse models, aiding expert interaction.
problem Lack of interaction between models and domain experts in classical machine learning.
method Approximate Rashomon set of sparse, generalized additive models using ellipsoids.
result Efficiently approximated Rashomon set facilitates model selection and exploration.
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.
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. Unsupervised deep learning is one of the most powerful representation learning techniques. Restricted Boltzman machine, sparse coding, regularized auto-encoders, and convolutional neural networks are pioneering building blocks of deep learning. In this paper, we propose a new building block -- distributed random models…
EBBS integrates expert assessments into MIO best-subsets problem.
problem Identifying relevant features in statistical models.
method Expert-implied Bayesian approach using MIO.
result Reduces to classical best-subsets when experts are silent.
We propose the first reduction-based approach to obtaining long-term memory guarantees for online learning in the sense of Bousquet and Warmuth, 2002, by reducing the problem to achieving typical switching regret. Specifically, for the classical expert problem with K actions and T rounds, using our framework we dev…
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.
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…
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.
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 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…
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.
SAIL learns from sub-optimal demonstrations to improve sample efficiency in sparse reward tasks.
problem Reducing sample complexity in sparse-rewarded tasks.
method Self-Adaptive Imitation Learning (SAIL) that exploits sub-optimal demonstrations and efficient exploration.
result Significantly improved sample efficiency and better final performance across various tasks.
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.
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 …
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.
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.
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. 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…
Creating maps is an essential task in robotics and provides the basis for effective planning and navigation. In this paper, we learn a compact and continuous implicit surface map of an environment from a stream of range data with known poses. For this, we create and incrementally adjust an ensemble of approximate Gauss…
We study how to effectively leverage expert feedback to learn sequential decision-making policies. We focus on problems with sparse rewards and long time horizons, which typically pose significant challenges in reinforcement learning. We propose an algorithmic framework, called hierarchical guidance, that leverages the…
Pairwise ranking aligns subjective clinical evaluations with objective indicators.
problem Aligning subjective clinical evaluations with objective indicators for improved diagnosis.
method Pairwise ranking methods to align subjective evaluations with objective indicators.
result The resulting score improves classification accuracy and provides a nuanced severity assessment.
We consider a variation on the problem of prediction with expert advice, where new forecasters that were unknown until then may appear at each round. As often in prediction with expert advice, designing an algorithm that achieves near-optimal regret guarantees is straightforward, using aggregation of experts. However, …
New method estimates graph compatibility from sparse labels.
problem Estimating graph compatibility from sparse labeled data.
method Factorized graph representations and algebraic amplification.
result End-to-end classification accuracy comparable to gold standard.
The importance of interpretability of machine learning models has been increasing due to emerging enterprise predictive analytics, threat of data privacy, accountability of artificial intelligence in society, and so on. Piecewise linear models have been actively studied to achieve both accuracy and interpretability. Th…