Analyze the dynamic stability of SGD
☆13Nov 25, 2018Updated 7 years ago
Alternatives and similar repositories for sgd.stability
Users that are interested in sgd.stability are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆15Apr 19, 2020Updated 6 years ago
- ☆10Apr 23, 2026Updated last month
- Training vision models with full-batch gradient descent and regularization☆40Feb 14, 2023Updated 3 years ago
- Datasets for Hyperparameter Optimization of Neural Machine Translation☆10Aug 19, 2024Updated last year
- 从Finnhub.io、Tiingo.com、新浪、腾讯、网易服务器提取全球证券数据，分析处理后存入数据库☆13Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- code to reproduce the empirical results in the research paper☆39Oct 12, 2021Updated 4 years ago
- Web上に公開されている小説をスクレイピングして青空文庫形式のテキストにする☆19Feb 9, 2017Updated 9 years ago
- Uniform Manifold Approximation and Projection☆13Oct 27, 2021Updated 4 years ago
- Official Implementation of "Transferring Inductive Biases Through Knowledge Distillation"☆15Jun 3, 2020Updated 6 years ago
- ☆10Aug 18, 2016Updated 9 years ago
- ☆13Oct 8, 2021Updated 4 years ago
- The PackNet Continual Learning Method in Pytorch☆15Aug 19, 2021Updated 4 years ago
- Full loss Hessian spectrum approximation tool.☆13Oct 9, 2019Updated 6 years ago
- Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians (ICML 2019)☆16Apr 27, 2019Updated 7 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆73Sep 25, 2024Updated last year
- Really fast readability☆19Apr 25, 2024Updated 2 years ago
- Belief Propagation Network for Hard Inductive Semi-Supervised Learning (IJCAI 2019)☆21Jul 6, 2023Updated 2 years ago
- Python implementation for Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces.☆13Nov 30, 2021Updated 4 years ago
- ☆10Apr 23, 2021Updated 5 years ago
- [ICML 2019] The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects☆15Apr 12, 2020Updated 6 years ago
- A second order optimizer for TensorFlow that uses the Saddle-Free method.☆22Feb 4, 2019Updated 7 years ago
- ☆17Feb 4, 2025Updated last year
- ☆21Jul 12, 2018Updated 7 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Code for the paper "Understanding the Role of Momentum in Stochastic Gradient Methods"☆14Oct 27, 2019Updated 6 years ago
- ☆18Oct 24, 2013Updated 12 years ago
- Chainer implementation of CIFAR-10 dataset training☆12Dec 7, 2022Updated 3 years ago
- Code and results accompanying our paper titled Leveraging Unlabeled Data to Predict Out-of-Distribution Performance at ICLR 2022☆10Dec 8, 2022Updated 3 years ago
- Github Repo for ICML 2022 paper: Communication-Efficient Adaptive Federated Learning☆10Nov 18, 2022Updated 3 years ago
- Experiments from our work Uncertainty Quantification and Deep Ensemble☆10Nov 1, 2021Updated 4 years ago
- Xmixers: A collection of SOTA efficient token/channel mixers☆28Sep 4, 2025Updated 9 months ago
- Make your openFrameworks window transparent☆24Jun 15, 2014Updated 11 years ago
- ☆13Mar 22, 2023Updated 3 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Hessian backpropagation (HBP): PyTorch extension of backpropagation for block-diagonal curvature matrix approximations☆22Mar 25, 2023Updated 3 years ago
- The code for the NeurIPS19 paper and blog on "Uniform convergence may be unable to explain generalization in deep learning".☆10Oct 26, 2019Updated 6 years ago
- Code for Accelerated Linearized Laplace Approximation for Bayesian Deep Learning (ELLA, NeurIPS 22')☆17Oct 12, 2022Updated 3 years ago
- ☆24Feb 15, 2020Updated 6 years ago
- Functional Regularisation for Continual Learning with Gaussian Processes☆15Oct 24, 2020Updated 5 years ago
- ☆10Mar 28, 2023Updated 3 years ago
- The Full Spectrum of Deepnet Hessians at Scale: Dynamics with SGD Training and Sample Size☆19May 19, 2019Updated 7 years ago