Picture for Julia Gusak

Julia Gusak

Quantization Aware Factorization for Deep Neural Network Compression

Add code
Aug 08, 2023
Figure 1 for Quantization Aware Factorization for Deep Neural Network Compression
Figure 2 for Quantization Aware Factorization for Deep Neural Network Compression
Figure 3 for Quantization Aware Factorization for Deep Neural Network Compression
Figure 4 for Quantization Aware Factorization for Deep Neural Network Compression
Viaarxiv icon

Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorch

Add code
Jul 03, 2023
Viaarxiv icon

Efficient GPT Model Pre-training using Tensor Train Matrix Representation

Add code
Jun 05, 2023
Viaarxiv icon

Survey on Large Scale Neural Network Training

Add code
Feb 21, 2022
Figure 1 for Survey on Large Scale Neural Network Training
Figure 2 for Survey on Large Scale Neural Network Training
Figure 3 for Survey on Large Scale Neural Network Training
Figure 4 for Survey on Large Scale Neural Network Training
Viaarxiv icon

Memory-Efficient Backpropagation through Large Linear Layers

Add code
Feb 02, 2022
Figure 1 for Memory-Efficient Backpropagation through Large Linear Layers
Figure 2 for Memory-Efficient Backpropagation through Large Linear Layers
Figure 3 for Memory-Efficient Backpropagation through Large Linear Layers
Figure 4 for Memory-Efficient Backpropagation through Large Linear Layers
Viaarxiv icon

Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction

Add code
Feb 02, 2022
Viaarxiv icon

Meta-Solver for Neural Ordinary Differential Equations

Add code
Mar 15, 2021
Figure 1 for Meta-Solver for Neural Ordinary Differential Equations
Figure 2 for Meta-Solver for Neural Ordinary Differential Equations
Figure 3 for Meta-Solver for Neural Ordinary Differential Equations
Figure 4 for Meta-Solver for Neural Ordinary Differential Equations
Viaarxiv icon

Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network

Add code
Aug 12, 2020
Figure 1 for Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network
Figure 2 for Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network
Figure 3 for Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network
Figure 4 for Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network
Viaarxiv icon

Towards Understanding Normalization in Neural ODEs

Add code
Apr 27, 2020
Figure 1 for Towards Understanding Normalization in Neural ODEs
Viaarxiv icon

Interpolated Adjoint Method for Neural ODEs

Add code
Mar 11, 2020
Figure 1 for Interpolated Adjoint Method for Neural ODEs
Figure 2 for Interpolated Adjoint Method for Neural ODEs
Figure 3 for Interpolated Adjoint Method for Neural ODEs
Figure 4 for Interpolated Adjoint Method for Neural ODEs
Viaarxiv icon