Multiresolution RNN improves dialogue response generation.
problem Generating relevant and on-topic responses in dialogue systems.
method Introducing a multiresolution recurrent neural network that models natural language generation as two parallel sequences.
result The model outperforms competing approaches in dialogue response generation on the Ubuntu domain and appears more relevant on Twitter.
We propose a multiresolution Gaussian process to capture long-range, non-Markovian dependencies while allowing for abrupt changes. The multiresolution GP hierarchically couples a collection of smooth GPs, each defined over an element of a random nested partition. Long-range dependencies are captured by the top-level GP…
Cisco introduces a new time series model for better forecasting.
problem Improving time series forecasting accuracy.
method Developed a new multiresolution decoder-only model trained on large datasets.
result The new model achieves superior performance on observability datasets.
NAOMI improves imputation accuracy for long-range sequences.
problem Missing value imputation in spatiotemporal data.
method Non-autoregressive deep generative model exploiting multiresolution structure.
result Significant improvement in imputation accuracy (60% reduction in average prediction error).
AV-ASR system improves speech recognition with visual context.
problem Improving speech recognition accuracy with visual information.
method Transformer-based architecture with multiresolution and multimodal training.
result Multiresolution training speeds up convergence and improves WER by 18%.
Extends MMF to nonsymmetric matrices for hierarchical structure.
problem Capturing hierarchical structure in nonsymmetric matrices.
method Multiresolution Matrix Factorization (MMF) extended to nonsymmetric matrices.
result Effective for matrix compression tasks, outperforming low-rank methods.
Paper proposes a new adaptive multiscale value function approximation for reinforcement learning.
problem Value function approximation in reinforcement learning with varying complexity.
method Adaptive multiscale approximation using multiresolution analysis and tree approximation.
result Convergence rate of the multiscale approximation is independent of basis function regularity.
Combining neural networks and multiscale decomposition for financial market analysis.
problem Financial markets' complexity and mainstream models' limitations in capturing non-linear structures.
method Neural networks for non-linear associations combined with multiscale decomposition.
result Improved understanding of financial market data substructures.
MKA improves Gaussian process regression for large datasets.
problem Gaussian process regression struggles with large datasets.
method MKA is a memory-efficient, direct kernel approximation method.
result MKA achieves better performance with small kernel length scales.
New algorithm uncovers hierarchical block structure in large matrices.
problem Uncovering hierarchical block structure in symmetric matrices.
method Incremental multiresolution matrix factorization.
result Algorithm scales well to large matrices and uncovers structure one feature at a time.
MathNet uses wavelets for graph representation and learning.
problem Graph Neural Networks (GNNs) for graph classification and regression.
method Multiresolution Haar-like wavelets, graph convolution, and pooling.
result MathNet achieves notable accuracy gains on graph classification and regression tasks.
This paper approximates scattered data using samplet coordinates with sparsity constraints.
problem Scattered data approximation with sparsity constraints.
method Samplet basis pursuit with ℓ1-regularization, multiresolution techniques, and semi-smooth Newton method. result The proposed method provides faster convergence and better signal sparsity compared to existing methods.
MRTL learns interpretable spatial patterns efficiently.
problem Efficient and interpretable spatial analysis in various fields.
method Multiresolution Tensor Learning (MRTL) algorithm.
result 4~5x speedup with accurate and interpretable latent factors.
New model captures long-range patterns in sequences efficiently.
problem Efficiently capturing long-range patterns in sequential data.
method Inspired by wavelet multiresolution analysis, introduces MultiresLayer with multiresolution convolution.
result State-of-the-art performance on sequence classification and autoregressive density estimation tasks.
Multiresolution Matrix Factorization (MMF) was recently introduced as a method for finding multiscale structure and defining wavelets on graphs/matrices. In this paper we derive pMMF, a parallel algorithm for computing the MMF factorization. Empirically, the running time of pMMF scales linearly in the dimension for spa…
The study develops methods to summarize team passing strategies from soccer data.
problem Modeling spatial passing networks across multiple games with varying positions.
method Multiresolution tensor decomposition and Poisson nonnegative block term decomposition.
result Automatic production of network motifs at different levels of detail.
In this letter we exhibit the relation between the isometries of a Riemannian contraction of a sub-Riemannian manifold and those of the sub-Riemannian metric, for to use this relation with two goals: establishing a result about the existence of fixed points of isometries groups; and the other, defining a Multiresolutio…
We introduce a near-linear complexity (geometric and meshless/algebraic) multigrid/multiresolution method for PDEs with rough (L∞) coefficients with rigorous a-priori accuracy and performance estimates. The method is discovered through a decision/game theory formulation of the problems of (1) identifying restri…
New model improves GP approximations by relaxing independence across resolutions.
problem Overfitting and non-smooth predictions in multiresolution GPs.
method Conditional independence among GPs across resolutions.
result Improved robustness against overfitting and smoother predictions.
Wavelet Kolmogorov-Arnold Networks improve federated learning performance.
problem Improving performance in federated learning with heterogeneous data.
method Implemented Wav-KAN with CWT and DWT for multiresolution capability, integrating wavelet-based activation functions.
result Significant improvements in computational efficiency, robustness, and accuracy in federated learning.
A new autoencoder architecture captures multiscale data.
problem Multiscale spatio-temporal data representation.
method Integrates multigrid methods, convolutional autoencoders, and transfer learning.
result Adaptive, hierarchical architecture captures different scaled features dynamically.
The study explores various localized bases and their duals for scattered data approximation.
problem Scattered data approximation using radial basis functions.
method Examines different localized bases including Lagrange, Newton, and multiresolution versions, and their duals.
result Localized orthogonal bases, such as the Newton basis, offer symmetric preconditioners and are feasible for scattered data approximation.
Delayed-RNN approximates stacked and bidirectional RNNs.
problem Improving RNN expressiveness and representational capacity.
method Weight-constrained delayed-RNN, equivalent to stacked-RNNs, with partial acausality.
result Delayed-RNN can approximate stacked and bidirectional RNNs, outperforming them in some tasks.
Automated robust solvers for arbitrary operators using game theory and Gaussian fields.
problem Developing scalable numerical solvers for any bounded linear operator.
method Formulating the problem as a game theory problem and using Gaussian fields to find optimal strategies.
result Introducing the Fast Gamblet Transform (FGT) for efficient linear system solving and eigenspace analysis.
In this work we consider the problem of detecting anomalous spatio-temporal behavior in videos. Our approach is to learn the normative multiframe pixel joint distribution and detect deviations from it using a likelihood based approach. Due to the extreme lack of available training samples relative to the dimension of t…
Finite precision RNNs have varying computational power, with LSTMs and ReLU-RNNs being more powerful.
problem Understanding the computational limits of finite precision RNNs for language recognition.
method Comparison of different RNN variants with finite precision and linear computation time.
result LSTMs and ReLU-RNNs are strictly stronger than other RNN variants in terms of computational power.
Compact RNNs reduce parameters and improve efficiency.
problem High computational cost of RNNs with large inputs.
method Block-Term Tensor Decomposition (BT-TD) to reduce RNN parameters.
result BT-RNN achieves better accuracy and faster convergence than standard RNNs.
PF-RNNs use particle filtering to model uncertainty in RNNs for better sequential data prediction.
problem Highly variable and noisy sequential data.
method PF-RNNs maintain a latent state distribution as a set of particles, updating with Bayes rule.
result PF-RNNs outperform standard RNNs on various sequence prediction tasks.
In this paper, we explore different ways to extend a recurrent neural network (RNN) to a \textit{deep} RNN. We start by arguing that the concept of depth in an RNN is not as clear as it is in feedforward neural networks. By carefully analyzing and understanding the architecture of an RNN, however, we find three points …
Transformer models outperform recurrent ones in modeling hierarchical data.
problem Modeling hierarchical structure in data.
method Introducing Multiresolution Transformer Networks leveraging self-attention.
result Multiresolution Transformer Networks significantly outperform state-of-the-art models on query suggestion datasets.
This paper studies a theoretical pruning method for RNNs to reduce computational costs.
problem High computational costs in recurrent neural networks (RNNs).
method Spectral pruning inspired approach for RNNs.
result Generalization error bounds for compressed RNNs are provided.
Lyapunov analysis improves RNN performance prediction.
problem Uncertainty in RNN performance prediction due to hyperparameters and architecture.
method Lyapunov spectral analysis of RNNs and Autoencoder-Lyapunov Embedding Learning (AeLLE).
result AeLLE successfully correlates RNN Lyapunov spectrum with accuracy and predicts performance.
In this work, we propose a novel recurrent neural network (RNN) architecture. The proposed RNN, gated-feedback RNN (GF-RNN), extends the existing approach of stacking multiple recurrent layers by allowing and controlling signals flowing from upper recurrent layers to lower layers using a global gating unit for each pai…
Proposes Fusion Recurrent Neural Network for sequence data.
problem Improving sequence learning for practical applications.
method Fusion module and Transport module for sequence data.
result Fusion RNN performs comparably to state-of-the-art RNNs.
MinimalRNN simplifies RNNs for better interpretability and efficiency.
problem Improving interpretability and efficiency of RNNs.
method MinimalRNN uses a simplified structure with minimal updates, leading to efficient learning and testing.
result MinimalRNN learns disentangled RNN states and captures longer range dependencies.
Interpretable RNN uses sparse recovery for better performance.
problem Interpreting the internal workings of RNNs.
method Sequential Sparse Recovery + SISTA algorithm.
result SISTA-RNN achieves better performance and is more interpretable.
Efficient RNN algorithm guarantees convergence in online learning.
problem Online nonlinear regression with RNNs.
method First-order training algorithm with convergence guarantee.
result The algorithm converges to optimum network parameters.
Diagonal RNNs improve music modeling performance and speed.
problem Improving symbolic music modeling efficiency and accuracy.
method Introduced diagonal recurrent matrices in RNNs for music modeling.
result Diagonal RNNs achieve better test likelihood and faster convergence.
Paper compresses RNNs for resource-constrained devices.
problem Difficulty deploying RNNs on resource-constrained devices.
method Uses Kronecker product (KP) to compress RNN layers.
result KP compresses RNN layers by 16-38x with minimal accuracy loss.
RNNs struggle with in-context retrieval, while Transformers excel.
problem In-context retrieval capability of RNNs.
method Theoretical analysis and experimental techniques (CoT, RAG, Transformer layer).
result Enhancing RNNs with techniques improves their in-context retrieval capability, closing the representation gap with Transformers.
GPU-optimized ES-RNN boosts time series forecasting speed by 322x.
problem Efficiently forecasting time series data.
method Vectorized GPU implementation of ES-RNN.
result Up to 322x speedup in training time.
Paper refines RNN training by analyzing smoothness and attractors.
problem Exploding and vanishing gradients in RNNs.
method Refined concept of exploding gradients using cost function smoothness.
result RNNs need to learn attractors to fully use their power.
R2N2 combines linear VAR and nonlinear RNN models for multivariate time series.
problem Multivariate time series modeling with poor predictive performance or complex models.
method R2N2 (Residual RNN) combines simple linear VAR and complex RNN models.
result R2N2 outperforms VAR and RNN alone, and is faster to train.
Novel method improves training RNNs by accelerating gradient descent.
problem Vanishing and exploding gradient problems in RNNs training.
method Adaptive stochastic Nesterov accelerated quasi-Newton method.
result Improved performance in training RNNs with low per-iteration cost.
ARNN augments RNNs with user-contextual preference for better session-based recommendations.
problem Limited context-awareness in RNN session models.
method Proposes ARNN that uses PNN to extract high-order user-contextual preference.
result ARNN outperforms baseline RNN by a large margin with rich user-side contexts.
Analyzes RNNs using ODEs to map their properties and improve stability.
problem Understanding and improving the stability of RNNs.
method Relates RNNs to ODEs, mapping their properties to integration methods.
result Establishes sufficient conditions for RNN training stability and designs new architectures.
AC-RNN improves RNN for sequence labeling tasks.
problem RNN's exposure bias in maximum-likelihood training.
method Actor-Critic training for RNNs.
result AC-RNN outperforms CRF on NER and CCG tagging.
Elman-type RNNs converge to globally optimal solutions in the mean-field regime.
problem Optimizing feature learning in wide RNNs.
method Analysis of gradient descent dynamics and mean-field limits.
result Fixed points of infinite-width dynamics are globally optimal.