Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

9172634 · Jun 202019922001200920182026
48 results for multiresolution RNN

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…

2012-09-05abs ↗pdf ↗

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.

This paper approximates scattered data using samplet coordinates with sparsity constraints.

problem Scattered data approximation with sparsity constraints.
method Samplet basis pursuit with 1\ell_1-regularization, multiresolution techniques, and semi-smooth Newton method.
result The proposed method provides faster convergence and better signal sparsity compared to existing methods.

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…

2015-07-15abs ↗pdf ↗

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.

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.

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.

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.

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 …

2013-12-20abs ↗pdf ↗

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.

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…

2015-02-09abs ↗pdf ↗

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.

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.

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.