ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure

Related tags

Deep Learningvivit
Overview

[ πŸ‘· πŸ— πŸ‘· πŸ— Coming soon! Official release with improved docs. Stay tuned. πŸ‘· πŸ— πŸ‘· πŸ— ]

ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure

Python 3.7+ [tests]

ViViT is a collection of numerical tricks to efficiently access curvature from the generalized Gauss-Newton (GGN) matrix based on its low-rank structure. Provided functionality includes computing

  • GGN eigenvalues
  • GGN eigenpairs (eigenvalues + eigenvector)
  • 1Λ’α΅—- and 2ⁿᡈ-order directional derivatives along GGN eigenvectors
  • Newton steps

These operations can also further approximate the GGN to reduce cost via sub-sampling, Monte-Carlo approximation, and block-diagonal approximation.

How does it work? ViViT uses and extends BackPACK for PyTorch. The described functionality is realized through a combination of existing and new BackPACK extensions and hooks into its backpropagation.

Installation

πŸ‘· πŸ— πŸ‘· πŸ— The PyPI release is coming soon. πŸ‘· πŸ— πŸ‘· πŸ—

For now, you need to install from GitHub via

pip install vivit-for-pytorch@git+https://github.com/f-dangel/vivit.git#egg=vivit-for-pytorch

Examples

πŸ‘· πŸ— πŸ‘· πŸ— Coming soon! πŸ‘· πŸ— πŸ‘· πŸ—

How to cite

If you are using ViViT, consider citing the paper

@misc{dangel2022vivit,
      title={{ViViT}: Curvature access through the generalized Gauss-Newton's low-rank structure},
      author={Felix Dangel and Lukas Tatzel and Philipp Hennig},
      year={2022},
      eprint={2106.02624},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
Comments
  • [ADD] Warn about instabilities if eigenvalues are small

    [ADD] Warn about instabilities if eigenvalues are small

    The directional gradient computation and transformation of the Newton step from Gram space into parameter space require division by the square root of the direction's eigenvalue. This is unstable if the eigenvalue is close to zero.

    opened by f-dangel 1
  • [ADD] Clean `DirectionalDampedNewtonComputation`

    [ADD] Clean `DirectionalDampedNewtonComputation`

    Adds directionally damped Newton step computation with cleaned up API.

    • Fixes a bug in the eigenvalue criterion in the tests. It always picked one more eigenvalue than specified.
    opened by f-dangel 1
  • [DOC] Add NTK example

    [DOC] Add NTK example

    Adds an example inspired by the functorch tutorial on NTKs. It demonstrates how to use vivit to compute empirical NTK matrices and makes a comparison with the functorch implementation.

    opened by f-dangel 1
  • [ADD] Simplify `DirectionalDerivatives` API

    [ADD] Simplify `DirectionalDerivatives` API

    Exotic features, like using different GGNs to compute directions and directional curvatures, as well as full control of which intermediate buffers to keep, have been deprecated in favor of a simpler API.

    • Remove Newton step computation for now as it was internally relying on DirectionalDerivatives
    • Remove many utilities and associated tests from the exotic features
    • Forbid duplicate indices in subsampling
    • Always delete intermediate buffers other than the target quantities
    opened by f-dangel 1
  • [DOC] Set up `sphinx` and RTD

    [DOC] Set up `sphinx` and RTD

    This PR adds a scaffold for the doc at https://vivit.readthedocs.io/en/latest/. Code examples are integrated via sphinx-gallery (I added a preliminary logo). Pull requests are built by the CI.

    To build the docs, run make docs. You need to install the dependencies first, for example using pip install -e .[docs].

    opened by f-dangel 1
  • Calculate Parameter Space Values of GGN Eigenvectors

    Calculate Parameter Space Values of GGN Eigenvectors

    The docs show how to calculate the gram matrix eigenvectors and the paper articulates that to translate from 'gram space' to parameter space we just need to multiply by the 'V' matrix.

    What's the easiest way of implementing this?

    question 
    opened by lk-wq 1
  • Detect loss function's `reduction`, error if unsupported

    Detect loss function's `reduction`, error if unsupported

    For now, the library only supports reduction='mean'. We rely on the user to use this reduction and raise awareness about this point in the documentation. It would be better to automatically have the library detect the reduction and error if it is unsupported.

    This can be done via a hook into BackPACK.

    • [ ] Implement hook that determines the loss function reduction during backpropagation
    • [ ] Integrate the above hook into the *Computation and raise an exception if the reduction is not supported
    • [ ] Remove the comments about supported reductions in the documentation
    enhancement 
    opened by f-dangel 0
Releases(1.0.0)
Owner
Felix Dangel
Machine Learning PhD student at the University of TΓΌbingen and the Max Planck Institute for Intelligent Systems.
Felix Dangel
GitHub Repository https://arxiv.org/abs/2106.02624
Official Pytorch implementation of "Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video", CVPR 2021

TCMR: Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video Qualtitative result Paper teaser video Introduction This r

Hongsuk Choi 215 Jan 06, 2023
For storing the complete exploration of Visual Question Answering for our B.Tech Project

Multi-Image vqa @authors: Akhilesh, Janhavi, Harsh Paper summary, Ideas tried and their corresponding results: on wiki Other discussions: on discussio

Harsh Raj 3 Jun 16, 2022
Implemented fully documented Particle Swarm Optimization algorithm (basic model with few advanced features) using Python programming language

Implemented fully documented Particle Swarm Optimization (PSO) algorithm in Python which includes a basic model along with few advanced features such as updating inertia weight, cognitive, social lea

9 Nov 29, 2022
Nerf pl - NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

nerf_pl Update: an improved NSFF implementation to handle dynamic scene is open! Update: NeRF-W (NeRF in the Wild) implementation is added to nerfw br

AIθ‘΅ 1.8k Dec 30, 2022
T2F: text to face generation using Deep Learning

⭐ [NEW] ⭐ T2F - 2.0 Teaser (coming soon ...) Please note that all the faces in the above samples are generated ones. The T2F 2.0 will be using MSG-GAN

Animesh Karnewar 533 Dec 22, 2022
LV-BERT: Exploiting Layer Variety for BERT (Findings of ACL 2021)

LV-BERT Introduction In this repo, we introduce LV-BERT by exploiting layer variety for BERT. For detailed description and experimental results, pleas

Weihao Yu 14 Aug 24, 2022
Omnidirectional Scene Text Detection with Sequential-free Box Discretization (IJCAI 2019). Including competition model, online demo, etc.

Box_Discretization_Network This repository is built on the pytorch [maskrcnn_benchmark]. The method is the foundation of our ReCTs-competition method

Yuliang Liu 266 Nov 24, 2022
The official code repo of "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection"

Hierarchical Token Semantic Audio Transformer Introduction The Code Repository for "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound

Knut(Ke) Chen 134 Jan 01, 2023
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19

2s-AGCN Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition in CVPR19 Note PyTorch version should be 0.3! For PyTor

LShi 547 Dec 26, 2022
πŸ₯ˆ78th place in Riiid Answer Correctness Prediction competition

Riiid Answer Correctness Prediction Introduction This repository is the code that placed 78th in Riiid Answer Correctness Prediction competition. Requ

Jungwoo Park 10 Jul 14, 2022
Official implementation of the paper Image Generators with Conditionally-Independent Pixel Synthesis https://arxiv.org/abs/2011.13775

CIPS -- Official Pytorch Implementation of the paper Image Generators with Conditionally-Independent Pixel Synthesis Requirements pip install -r requi

Multimodal Lab @ Samsung AI Center Moscow 201 Dec 21, 2022
PyTorch Implementation of Spatially Consistent Representation Learning(SCRL)

Spatially Consistent Representation Learning (CVPR'21) Official PyTorch implementation of Spatially Consistent Representation Learning (SCRL). This re

Kakao Brain 102 Nov 03, 2022
Official implementation of VQ-Diffusion

Official implementation of VQ-Diffusion: Vector Quantized Diffusion Model for Text-to-Image Synthesis

Microsoft 592 Jan 03, 2023
NLMpy - A Python package to create neutral landscape models

NLMpy is a Python package for the creation of neutral landscape models that are widely used by landscape ecologists to model ecological patterns

Manaaki Whenua – Landcare Research 1 Oct 08, 2022
Official implementation of the paper DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows

DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows Official implementation of the paper DeFlow: Learning Complex Im

Valentin Wolf 86 Nov 16, 2022
Official implementation of the paper "Steganographer Detection via a Similarity Accumulation Graph Convolutional Network"

SAGCN - Official PyTorch Implementation | Paper | Project Page This is the official implementation of the paper "Steganographer detection via a simila

ZHANG Zhi 1 Nov 26, 2021
Multi-modal Vision Transformers Excel at Class-agnostic Object Detection

Multi-modal Vision Transformers Excel at Class-agnostic Object Detection

Muhammad Maaz 206 Jan 04, 2023
Automatic learning-rate scheduler

AutoLRS This is the PyTorch code implementation for the paper AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly published

Yuchen Jin 33 Nov 18, 2022
The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".

Watermark-Robustness-Toolbox - Official PyTorch Implementation This repository contains the official PyTorch implementation of the following paper to

49 Dec 19, 2022
Code release for the paper β€œWorldsheet Wrapping the World in a 3D Sheet for View Synthesis from a Single Image”, ICCV 2021.

Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image This repository contains the code for the following paper: R. Hu,

Meta Research 37 Jan 04, 2023