allenai / hidden-networks
☆182Updated 3 years ago
Related projects: ⓘ
- ☆215Updated last month
- Code for "Picking Winning Tickets Before Training by Preserving Gradient Flow" https://openreview.net/pdf?id=SkgsACVKPH☆97Updated 4 years ago
- Train ImageNet *fast* in 500 lines of code with FFCV☆135Updated 4 months ago
- ☆142Updated last year
- Mode Connectivity and Fast Geometric Ensembles in PyTorch☆262Updated last year
- Soft Threshold Weight Reparameterization for Learnable Sparsity☆88Updated last year
- ☆153Updated 2 years ago
- Code accompanying the NeurIPS 2020 paper: WoodFisher (Singh & Alistarh, 2020)☆45Updated 3 years ago
- Reproduction and analysis of SNIP paper☆28Updated 4 years ago
- SNIP: SINGLE-SHOT NETWORK PRUNING BASED ON CONNECTION SENSITIVITY☆108Updated 5 years ago
- ☆133Updated 3 years ago
- End-to-end training of sparse deep neural networks with little-to-no performance loss.☆315Updated last year
- [ICLR 2020] Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks☆137Updated 3 years ago
- Identify a binary weight or binary weight and activation subnetwork within a randomly initialized network by only pruning and binarizing …☆48Updated 2 years ago
- ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."☆114Updated last year
- {KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch☆204Updated last month
- Implementation of Continuous Sparsification, a method for pruning and ticket search in deep networks☆32Updated 2 years ago
- Pytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.☆101Updated 5 years ago
- Code for "Supermasks in Superposition"☆115Updated 11 months ago
- Pytorch implementation of KFAC and E-KFAC (Natural Gradient).☆125Updated 5 years ago
- A research library for pytorch-based neural network pruning, compression, and more.☆161Updated last year
- Efficient PyTorch Hessian eigendecomposition tools!☆355Updated 6 months ago
- ☆81Updated 4 years ago
- Code for Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot☆43Updated 3 years ago
- PyTorch implementation of Mixer-nano (#parameters is 0.67M, originally Mixer-S/16 has 18M) with 90.83 % acc. on CIFAR-10. Training from s…☆28Updated 2 years ago
- Lightweight torch implementation of rigl, a sparse-to-sparse optimizer.☆55Updated 2 years ago
- ☆118Updated 3 months ago
- This repository contains a Pytorch implementation of the paper "The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks"…☆321Updated 11 months ago
- Code release for REPAIR: REnormalizing Permuted Activations for Interpolation Repair☆43Updated 7 months ago
- ☆70Updated 4 years ago