Code to reproduce the experiments from our NeurIPS 2021 paper " The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective"

Last update: Dec 12, 2022

Related tags

Overview

Code

To run:

python runner.py new --save <SAVE_NAME> --data <PATH_TO_DATA_DIR> --dataset <DATASET> --model <model_name> [options] --n 1000 - train - test - kernel_fit - done

Options for Bayesian regression models are:

gp
gp_3l
gp_acos
gp_acos3
deep_gp_svi (options: --width 2)
deep_gp_hmc (options: --width 2)
deep_gp_3l2l_hmc (options: --width 2)
deep_gp_3l3l_hmc (options: --width1 2 --width2 2)
nn_hmc (options: --width 2)
nn_3l_hmc (options: --width 2)

Options for non-Bayesian classification models are:

nn (options: --widths 16,32,32)
lenet (options: --width 256 --conv-width 16)
resnet (options: --depth 14 --width 64)

Owner

Geoff Pleiss

GitHub Repository

A unified framework for machine learning with time series

Welcome to sktime A unified framework for machine learning with time series We provide specialized time series algorithms and scikit-learn compatible

6k Jan 08, 2023

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

MVSNeRF Project page | Paper This repository contains a pytorch lightning implementation for the ICCV 2021 paper: MVSNeRF: Fast Generalizable Radiance

529 Dec 30, 2022

Implementation of parameterized soft-exponential activation function.

Soft-Exponential-Activation-Function: Implementation of parameterized soft-exponential activation function. In this implementation, the parameters are

1 Feb 23, 2022

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion

364 Jan 03, 2023

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging This repository contains an implementation

1.1k Jan 02, 2023

constructing maps of intellectual influence from publication data

Influencemap Project @ ANU Influence in the academic communities has been an area of interest for researchers. This can be seen in the popularity of a

13 Jun 18, 2022

A Pytorch Implementation of ClariNet

ClariNet A Pytorch Implementation of ClariNet (Mel Spectrogram -- Waveform) Requirements PyTorch 0.4.1 & python 3.6 & Librosa Examples Step 1. Downlo

286 Sep 15, 2022

Implementation of Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021).

Self-supervised Graph-level Representation Learning with Local and Global Structure Introduction This project is an implementation of ``Self-supervise

50 Dec 09, 2022

Official implementation of the article "Unsupervised JPEG Domain Adaptation For Practical Digital Forensics"

Unsupervised JPEG Domain Adaptation for Practical Digital Image Forensics @WIFS2021 (Montpellier, France) Rony Abecidan, Vincent Itier, Jeremie Boulan

6 Jan 06, 2023

Meli Data Challenge 2021 - First Place Solution

My solution for the Meli Data Challenge 2021

23 Mar 09, 2022

SPTAG: A library for fast approximate nearest neighbor search

SPTAG: A library for fast approximate nearest neighbor search SPTAG SPTAG (Space Partition Tree And Graph) is a library for large scale vector approxi

4.3k Jan 01, 2023

Code and model benchmarks for "SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology"

NeurIPS 2020 SEVIR Code for paper: SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology Requirement

46 Dec 15, 2022

Code to reproduce the experiments from our NeurIPS 2021 paper " The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective"

Related tags

Overview

Code

Owner

Geoff Pleiss

A unified framework for machine learning with time series

[ICCV 2021] Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

Implementation of parameterized soft-exponential activation function.

[CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

constructing maps of intellectual influence from publication data

A Pytorch Implementation of ClariNet

Implementation of Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021).

Official implementation of the article "Unsupervised JPEG Domain Adaptation For Practical Digital Forensics"

Meli Data Challenge 2021 - First Place Solution

SPTAG: A library for fast approximate nearest neighbor search

Code and model benchmarks for "SEVIR : A Storm Event Imagery Dataset for Deep Learning Applications in Radar and Satellite Meteorology"

Calling Julia from Python - an experiment on data loading

A comprehensive and up-to-date developer education platform for Urbit.

Source code for EquiDock: Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking (ICLR 2022)

VolumeGAN - 3D-aware Image Synthesis via Learning Structural and Textural Representations

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)

Multi-objective gym environments for reinforcement learning.

Neural HMMs are all you need (for high-quality attention-free TTS)

Graph parsing approach to structured sentiment analysis.