uclnlp / torch-imleLinks
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions
☆259Updated 2 years ago
Alternatives and similar repositories for torch-imle
Users that are interested in torch-imle are comparing it to the libraries listed below
Sorting:
- Differentiable Sorting Networks☆125Updated 2 years ago
- ☆153Updated 5 years ago
- Differentiable Algorithms and Algorithmic Supervision.☆116Updated 2 years ago
- ☆100Updated 4 years ago
- Stochastic Automatic Differentiation library for PyTorch.☆208Updated last year
- This library would form a permanent home for reusable components for deep probabilistic programming. The library would form and harness a…☆310Updated last month
- A Machine Learning workflow for Slurm.☆152Updated 5 years ago
- Named tensors with first-class dimensions for PyTorch☆332Updated 2 years ago
- ☆214Updated 4 years ago
- A pure-functional implementation of a machine learning transformer model in Python/JAX☆181Updated 9 months ago
- Tensorflow implementation and notebooks for Implicit Maximum Likelihood Estimation☆67Updated 3 years ago
- This repository contains the results for the paper: "Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers"☆184Updated 4 years ago
- A Pytree Module system for Deep Learning in JAX☆214Updated 2 years ago
- 🧀 Pytorch code for the Fromage optimiser.☆129Updated last year
- Cockpit: A Practical Debugging Tool for Training Deep Neural Networks☆488Updated 3 years ago
- Official code for the Stochastic Polyak step-size optimizer☆139Updated last year
- Library that contains implementations of machine learning components in the hyperbolic space☆145Updated last year
- Code for our NeurIPS 2022 paper☆371Updated 3 years ago
- Convert scikit-learn models to PyTorch modules☆168Updated last year
- ☆163Updated 2 years ago
- Lightweight Hyperparameter Optimization 🚂☆149Updated last year
- ☆71Updated 2 years ago
- An alternative to convolution in neural networks☆259Updated last year
- Neural Turing Machines in pytorch☆49Updated 4 years ago
- Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes…☆249Updated 5 years ago
- Code accompanying our paper "Feature Learning in Infinite-Width Neural Networks" (https://arxiv.org/abs/2011.14522)☆62Updated 4 years ago
- Official codebase for Pretrained Transformers as Universal Computation Engines.☆246Updated 4 years ago
- Fast Discounted Cumulative Sums in PyTorch☆97Updated 4 years ago
- A custom PyTorch layer that is capable of implementing extremely wide and sparse linear layers efficiently☆51Updated 2 years ago
- Parameter-Free Optimizers for Pytorch☆130Updated last year