Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets

No abstract is available for this paper.

• Publication year

  2013

• Venue

  IEEE International Conference on Acoustics, Speech, and Signal Processing

• Publication date

  2013-05-26

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICASSP.2013.6638949
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep convolutional neural networks for LVCSR

  2013cited by this paper
• Parallel stochastic gradient algorithms for large-scale matrix completion

  2013cited by this paper
• Deep Neural Network Language Models

  2012cited by this paper
• Deep Neural Networks for Acoustic Modeling in Speech Recognition

  2012cited by this paper
• Scalable Minimum Bayes Risk Training of Deep Neural Network Acoustic Models Using Distributed Hessian-free Optimization

  2012cited by this paper
• Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups

  2012cited by this paper
• Conversational Speech Transcription Using Context-Dependent Deep Neural Networks

  2012influential reference
• Making Deep Belief Networks effective for large vocabulary continuous speech recognition

  2011influential reference
• Feature engineering in Context-Dependent Deep Neural Networks for conversational speech transcription

  2011cited by this paper
• The IBM Attila speech recognition toolkit

  2010cited by this paper
• Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine

  2010cited by this paper
• Introduction to linear Algebra

  2010cited by this paper
• Performance Prediction for Exponential Language Models

  2009cited by this paper
• Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling

  2009influential reference
• Dimension reduction and coefficient estimation in multivariate linear regression

  2007cited by this paper
• To recognize shapes, first learn to generate images.

  2007cited by this paper
• Convolutional networks for images, speech, and time series

  1998cited by this paper
• Connectionist Speech Recognition: A Hybrid Approach

  1993cited by this paper

• Improve NNLMs by text generation from pre-trained language models

  2026cites this paper
• Agile Reinforcement Learning through Separable Neural Architecture

  2026cites this paper
• Why LoRA Resists Label Noise: A Theoretical Framework for Noise-Robust Parameter-Efficient Fine-Tuning

  2026cites this paper
• A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?

  2025cites this paper
• Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture

  2025cites this paper
• Adaptive focusing for wideband beamforming in multipath environments.

  2025cites this paper
• Mobile medical systems for equitable healthcare

  2025cites this paper
• Quantification stochastic configuration networks with incremental encoding

  2025cites this paper
• Energy Considerations for Large Pretrained Neural Networks

  2025cites this paper
• Low-Rank Matrix Approximation for Neural Network Compression

  2025cites this paper
• A survey of model compression techniques: past, present, and future

  2025cites this paper
• LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation

  2025cites this paper
• QTTARNN: A Highly‐Efficient Attention Driven Quantized Tensor Train Recursive Neural Network for Cyber‐Physical‐Social Intelligence

  2025cites this paper
• A Feature Map Fusion Self-Distillation Scheme for Image Classification Networks

  2025cites this paper
• CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation

  2025cites this paper
• Position: AI Scaling: From Up to Down and Out

  2025cites this paper
• An Accuracy-Preserving Neural Network Compression via Tucker Decomposition

  2025cites this paper
• Lightweight Class Incremental Semantic Segmentation Without Catastrophic Forgetting

  2025cites this paper
• Compression of Convolutional Neural Networks Employing Tensor Train and High Dimensional Model Representation

  2025cites this paper
• Splitting-based randomized dynamical low-rank approximations for stiff matrix differential equations

  2025cites this paper
• TER-FCN: Tensor Einstein Reduced Fully Connected Network applied to Region-based Convolutional Neural Networks for object detection

  2025cites this paper
• LatentLLM: Attention-Aware Joint Tensor Compression

  2025cites this paper
• A Low-Complexity Structured Neural Network Approach to Intelligently Realize Wideband Multi-Beam Beamformers

  2025cites this paper
• NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks

  2025cites this paper
• Shell-Guided Compression of Voxel Radiance Fields

  2025cites this paper
• Ant Colony Optimization for Low-Rank Factorization with DNN on People Counting IoT using Environmental Sensors

  2025cites this paper
• Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training

  2025cites this paper
• Element-wise Modulation of Random Matrices for Efficient Neural Layers

  2025cites this paper
• Spatial Spiking Neural Networks Enable Efficient and Robust Temporal Computation

  2025cites this paper
• ASQ & POST: A synergistic framework for adaptive and non-uniform quantization

  2025cites this paper
• Concept Layers: Enhancing Interpretability and Intervenability via LLM Conceptualization

  2025cites this paper
• Precision Neural Network Quantization via Learnable Adaptive Modules

  2025cites this paper
• A Systematic Literature Review on Multimodal Text Summarization

  2025cites this paper
• Binary SqueezeNet: Enhancing Parameter Efficiency in Binary Neural Networks

  2025cites this paper
• YOLO-NAS Based Low-Power CNN Hardware for Digital Number Recognition: Design, Optimization, and Implementation

  2025cites this paper
• ERGo: Energy-Efficient Hybrid Graph Neural Network Training on Processing-in-Memory Architectures

  2025cites this paper
• LRAT: Low-Rank Adaptive Transformer for end-to-end speech recognition

  2025cites this paper
• Secure and Storage-Efficient Deep Learning Models for Edge AI Using Automatic Weight Generation

  2025cites this paper
• Real-Time Semantic Segmentation: A Comprehensive Review and Future Perspectives

  2025cites this paper
• LT-OAQ: Learnable Threshold Based Outlier-Aware Quantization and its Energy-Efficient Accelerator for Low-Precision On-Chip Training

  2025cites this paper
• INSIGHT: A Survey of In-Network Systems for Intelligent, High-Efficiency AI and Topology Optimization

  2025cites this paper
• Structure-Aware Automatic Channel Pruning by Searching with Graph Embedding

  2025cites this paper
• Model Compression vs. Adversarial Robustness: An Empirical Study on Language Models for Code

  2025cites this paper
• The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning

  2025cites this paper
• AI Scaling: From Up to Down and Out

  2025cites this paper
• VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits

  2025cites this paper
• Vanishing Contributions: A Unified Approach to Smoothly Transition Neural Models into Compressed Form

  2025cites this paper
• On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization

  2025cites this paper
• Filter Pruning and Knowledge Distillation for Efficient Source-Free Unsupervised Domain Adaptation

  2025cites this paper
• Partial Filter-Sharing: Improved Parameter-sharing Method for Single Image Super-Resolution Networks

  2025cites this paper
• MLLM-ITV: A Multimodal Large Language Model for Image-to-Text Generation Based on Vertical Sector

  2025cites this paper
• Meta-Sparsity: Learning Optimal Sparse Structures in Multi-task Networks through Meta-learning

  2025cites this paper
• Low-rank perturbation adjustment (LoPA): An implicit regularization method in image classification

  2025cites this paper
• Tiny Federated Wireless Foundation Models for Resource-Constrained Devices

  2025cites this paper
• DECA: Dual error curves analysis for out-of-distribution detection via low-rank decomposition

  2025cites this paper
• Dynamic Rank Reinforcement Learning for Adaptive Low-Rank Multi-Head Self Attention in Large Language Models

  2025cites this paper
• Optimising TinyML with quantization and distillation of transformer and mamba models for indoor localisation on edge devices

  2024cites this paper
• Krony-PT: GPT-2 Compressed with Kronecker Products

  2024cites this paper
• TEC-CNN: Toward Efficient Compressing of Convolutional Neural Nets with Low-rank Tensor Decomposition

  2024cites this paper
• SoftLMs: Efficient Adaptive Low-Rank Approximation of Language Models using Soft-Thresholding Mechanism

  2024cites this paper
• Pr-Ge-Ne: Efficient Encoding of Pervasive Video Sensing Streams by Pruned Generative Networks

  2024cites this paper
• Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models

  2024cites this paper
• Novel Post-Training Structure-Agnostic Weight Pruning Technique for Deep Neural Networks

  2024cites this paper
• LoRTA: Low Rank Tensor Adaptation of Large Language Models

  2024cites this paper
• Accelerated alternating minimization algorithm for low-rank approximations in the Chebyshev norm

  2024cites this paper
• FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees

  2024cites this paper
• QGAN: Low Footprint Quaternion Neural Vocoder for Speech Synthesis

  2024cites this paper
• On the atout ticket learning problem for neural networks and its application in securing federated learning exchanges

  2024cites this paper
• Revealing the Utilized Rank of Subspaces of Learning in Neural Networks

  2024cites this paper
• An Approach to Pruning the Structure of Convolutional Neural Networks without Loss of Generalization Ability

  2024cites this paper
• Computer Vision Model Compression Techniques for Embedded Systems:A Survey

  2024cites this paper
• Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees

  2024cites this paper
• Structured and Balanced Multi-component and Multi-layer Neural Networks

  2024influential citation
• Speech and Language Recognition with Low-rank Adaptation of Pretrained Models

  2024cites this paper
• Structured Bayesian Federated Learning for Green AI: A Decentralized Model Compression Using Turbo-VBI-Based Approach

  2024cites this paper
• Enhancing Chinese comprehension and reasoning for large language models: an efficient LoRA fine-tuning and tree of thoughts framework

  2024cites this paper
• TinyPower: Side-Channel Attacks with Tiny Neural Networks

  2024cites this paper
• Vertical LoRA: Dense Expectation-Maximization Interpretation of Transformers

  2024cites this paper
• OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models

  2024cites this paper
• Spectral Tensor Layers for Communication-Free Distributed Deep Learning

  2024cites this paper
• Mobile-friendly skin lesion detection using an attention-driven lightweight model

  2024cites this paper
• Reweighted Solutions for Weighted Low Rank Approximation

  2024cites this paper
• An Empirical Investigation of Matrix Factorization Methods for Pre-trained Transformers

  2024cites this paper
• Spectral Adapter: Fine-Tuning in Spectral Space

  2024cites this paper
• An Agile Super-Resolution Network via Intelligent Path Selection

  2024cites this paper
• DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization

  2024cites this paper
• Low-rank Adaptation for Spatio-Temporal Forecasting

  2024cites this paper
• LLaMA-LoRA Neural Prompt Engineering: A Deep Tuning Framework for Automatically Generating Chinese Text Logical Reasoning Thinking Chains

  2024cites this paper
• CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations

  2024cites this paper
• Data Privacy-Preserving and Communication Efficient Federated Multilinear Compressed Learning

  2024cites this paper
• TetriX: Flexible Architecture and Optimal Mapping for Tensorized Neural Network Processing

  2024cites this paper
• A Practical Approach for Employing Tensor Train Decomposition in Edge Devices

  2024cites this paper
• Efficient Real-Time Human Activity Recognition with IoT Sensor Data Using Conditionally Parametrized Convolutions

  2024cites this paper
• Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

  2024cites this paper
• Neural Network Compression Based on Tensor Ring Decomposition

  2024cites this paper
• SS1: Accelerating Inference with Fast and Expressive Sketch Structured Transform

  2024cites this paper
• Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward

  2024cites this paper
• Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning

  2024cites this paper
• Convolutional Neural Network Compression via Dynamic Parameter Rank Pruning

  2024cites this paper
• A new approach to neural networks using pseudo-differential operators

  2024cites this paper