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.
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.
Long Short-Term Memory (LSTM) infers the long term dependency through a cell state maintained by the input and the forget gate structures, which models a gate output as a value in [0,1] through a sigmoid function. However, due to the graduality of the sigmoid function, the sigmoid gate is not flexible in representing m…
Gated recurrent neural networks have achieved remarkable results in the analysis of sequential data. Inside these networks, gates are used to control the flow of information, allowing to model even very long-term dependencies in the data. In this paper, we investigate whether the original gate equation (a linear projec…
Improved logistic MoE with sigmoid gate shows better sample efficiency.
problem Improving sample efficiency in logistic MoE models.
method Comprehensive analysis of multinomial logistic MoE with modified sigmoid gate, incorporating temperature parameter and using Euclidean score.
result The sigmoid gate leads to lower sample complexity than softmax gate for both parameter and expert estimation.
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.
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.
The paper establishes convergence rates for MoE models in classification problems.
problem Understanding the behavior of MoE models in classification settings.
method Established convergence rates for density and parameter estimation in softmax gating multinomial logistic MoE models.
result Parameter estimation rates are significantly improved with a novel modified softmax gating function.
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 …
Paper connects MoE and self-attention, proposing active-attention.
problem Improving efficiency and performance of self-attention mechanisms.
method Established connection between MoE and self-attention, analyzed quadratic gating functions, proposed active-attention mechanism.
result Active-attention outperforms standard self-attention in various tasks.
Temporal Functional Circuits explain KAN forecasts with interpretable edge functions.
problem Lack of mechanistic explanations in KAN forecasting.
method Transform KAN edge functions into faithful, temporally grounded explanations using a gated residual KAN.
result Gated KAN achieves lower MSE than linear-only models on regime-switching signals.
Architecture optimization, which is a technique for finding an efficient neural network that meets certain requirements, generally reduces to a set of multiple-choice selection problems among alternative sub-structures or parameters. The discrete nature of the selection problem, however, makes this optimization difficu…
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.
LSTMs were introduced to combat vanishing gradients in simple RNNs by augmenting them with gated additive recurrent connections. We present an alternative view to explain the success of LSTMs: the gates themselves are versatile recurrent models that provide more representational power than previously appreciated. We do…
Analyzes convergence rates for Gaussian-gated MoE model.
problem Theoretical understanding of Gaussian-gated MoE model is incomplete.
method Maximum likelihood estimation with novel Voronoi loss functions.
result MLE has distinct behaviors under different settings of Gaussian gating function parameters.
Monotone neural networks can approximate and interpolate functions efficiently.
problem Understanding the efficiency and expressiveness of monotone neural networks.
method Solving the monotone interpolation problem using depth-4 networks and comparing size bounds with arbitrary networks.
result Monotone neural networks can approximate and interpolate functions efficiently, but may require exponential size in high dimensions.
This work interprets GELU and related activations via a first-order loss function.
problem Understanding and optimizing activation functions in neural networks.
method Complementary interpretation using the Gaussian first-order loss function.
result Calibrated or learned uniform-threshold gates are competitive and often outperform GELU, ReLU, and SiLU/Swish.
Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional, long short-term memory (convLSTM) modules. We introduce a novel reduced-gate convolutional LSTM(rgcLSTM) architecture that…
Model accurately gates ocean microbes from high-frequency flow cytometry data.
problem Gating of high-frequency flow cytometry data for ocean microbes is challenging.
method Trend filtered mixture of experts with smooth parameter variation.
result Model accurately matches human-annotated gating and corrects errors.
Gating is a key technique used for integrating information from multiple sources by long short-term memory (LSTM) models and has recently also been applied to other models such as the highway network. Although gating is powerful, it is rather expensive in terms of both computation and storage as each gating unit uses a…
A new method selects features for clustering without labels.
problem Identifying meaningful features in large datasets.
method Differentiable unsupervised feature selection using a gated Laplacian.
result The method improves clustering performance in noisy data.
The paper studies 4-qubit Clifford states and their properties.
problem Understanding the set and properties of 4-qubit Clifford states.
method Analyzing the 293760 4-qubit Clifford states, splitting them into 18 groups, and studying the action of CNOT gates and local gates.
result There are 293760 4-qubit Clifford states with specific entanglement entropies, and any pair can be connected with local gates and at most 3 CNOT gates.
New method prepares 3-qubit states using local gates and controlled-Z gates.
problem Preparation of 3-qubit states using quantum gates.
method Uses Ry(θ) gates and controlled-Z gates, with an optimal number of controlled-Z gates. result Optimal number of controlled-Z gates for preparing 3-qubit states is four. We propose a novel adaptive approximation approach for test-time resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gat…
We present a dynamic model selection approach for resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gating and predict…
In quantum computation, series of quantum gates have to be arranged in a predefined sequence that led to a quantum circuit in order to solve a particular problem. What if the sequence of quantum gates is known but both the problem to be solved and the outcome of the so defined quantum circuit remain in the shadow? This…
GLU variants improve Transformer performance.
problem Improving the performance of Transformer models.
method Tested variations of Gated Linear Units (GLU) in Transformer feed-forward sublayers.
result Some GLU variants yield better performance than ReLU or GELU activations.
Investigates the fundamental components of attention mechanisms.
problem Understanding the building blocks of attention in deep learning.
method Classified and studied three key mechanisms: additive, multiplicative output, and synaptic attention.
result Additive activation attention is central in proofs of lower bounds.
Unified framework for SGMoE resolves estimation and selection issues.
problem Non-identifiability, coupled differential relations, and tight coupling in softmax-Gated models.
method Unified statistical framework with Voronoi-type loss functions and dendrograms of mixing measures.
result Consistent selection of the number of experts without model sweeps, optimal parameter rates under overfitting.
This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs). What distinguishes GLNs from contemporary neural networks is the distributed and local nature of their credit assignment mechanism; each neuron directly predicts the target, forgoing the ability to learn feature…
Study stability of selective SSMs with discontinuous gating.
problem Challenges in stability analysis of selective SSMs with discontinuous gating.
method Passivity and Input-to-State Stability (ISS) analysis of continuous-time selective SSMs.
result Derivation of sufficient conditions for global ISS with respect to the port input.
Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolutional networks (convnets), incorporating rectifier units and max-pooling, are neither smooth nor convex. Standard guarantees therefore do n…
For any positive integer k, there exist neural networks with Θ(k3) layers, Θ(1) nodes per layer, and Θ(1) distinct parameters which can not be approximated by networks with O(k) layers unless they are exponentially large --- they must possess Ω(2k) nodes. This result is proved here for a class o…
Gated attention improves model curvature, enhancing performance on nonlinear tasks.
problem Understanding the geometric implications of gating in attention mechanisms.
method Modeling attention outputs as Gaussian distributions and analyzing Fisher--Rao geometry.
result Gated attention enables non-flat geometries, including positively curved manifolds.
Gated attention improves performance by using a hierarchical mixture of experts.
problem Improving performance of self-attention mechanisms in Transformers.
method Rigorously show that gated attention can be modeled as a hierarchical mixture of experts, providing a theoretical justification for its benefits.
result Gated attention is more sample-efficient than multi-head self-attention, requiring fewer data points to achieve the same estimation error.
Given the success of the gated recurrent unit, a natural question is whether all the gates of the long short-term memory (LSTM) network are necessary. Previous research has shown that the forget gate is one of the most important gates in the LSTM. Here we show that a forget-gate-only version of the LSTM with chrono-ini…
Gating units in GRUs and LSTMs create slow modes and control phase-space complexity.
problem Training challenges in RNNs due to exploding or vanishing gradients.
method Random matrix theory and mean-field theory applied to GRUs and LSTMs.
result Gates in GRUs and LSTMs lead to accumulation of slow modes and control phase-space complexity.
The paper evaluates three variants of the Gated Recurrent Unit (GRU) in recurrent neural networks (RNN) by reducing parameters in the update and reset gates. We evaluate the three variant GRU models on MNIST and IMDB datasets and show that these GRU-RNN variant models perform as well as the original GRU RNN model while…
Paper proposes a novel method to accurately determine the number of experts in Gaussian-gated Gaussian MoE models.
problem Challenges in model selection for MoE models, especially with covariates.
method Introduces a novel extension using dendrograms of mixing measures to estimate the true number of mixture components.
result Achieves optimal convergence rates for parameter estimation and accurately approximates the regression function.
We propose a practical method for L0 norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularization is interesting since (1) it can greatly speed up training and inference, and (2) it can improve generalization. AIC and BIC, well-known …
This study analyzes communication constraints in MoE architectures using information theory.
problem Communication constraints in Mixture-of-Experts (MoE) architectures.
method Developed a rate-distortion characterization of finite-rate gating in MoE architectures using information theory.
result Yielded capacity-aware limits for communication-constrained MoE systems.
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.
Bayesian methods have been successfully applied to sparsify weights of neural networks and to remove structure units from the networks, e. g. neurons. We apply and further develop this approach for gated recurrent architectures. Specifically, in addition to sparsification of individual weights and neurons, we propose t…
A framework for modular training of robust generative models.
problem Training large generative models is resource-intensive and requires heuristic tuning.
method Modular training using a gating mechanism and a minimax game to find a robust gate.
result The modular approach can theoretically outperform monolithic baselines and is scalable.
Cortical circuits exhibit intricate recurrent architectures that are remarkably similar across different brain areas. Such stereotyped structure suggests the existence of common computational principles. However, such principles have remained largely elusive. Inspired by gated-memory networks, namely long short-term me…
GKP codes connect quantum gates to algebraic curves, enabling fault-tolerant quantum computation.
problem Implementing fault-tolerant quantum computation in quantum harmonic oscillator systems.
method Exploring the topological and algebraic structure of GKP codes, showing how gates correspond to symplectic automorphisms and mapping class groups of surfaces.
result GKP Clifford gates are identified with symplectic automorphisms of GKP lattices and mapping class groups of surfaces, providing a topological interpretation of fault tolerance.
GLCB uses Gated Linear Networks for online contextual bandits.
problem Online learning in contextual bandits with uncertainty estimation.
method Gated Linear Networks (GLNs) for prediction and uncertainty estimation.
result GLCB outperforms state-of-the-art methods in online contextual bandits.
APINNs improve physics-informed neural networks through flexible domain decomposition.
problem Improving physics-informed neural networks (PINNs) for solving partial differential equations (PDEs).
method Introduces a trainable gate network for soft domain decomposition, allowing flexible parameter sharing and improved generalization.
result APINNs significantly improve PINNs and XPINNs, demonstrating better performance on various types of PDEs.