# Stochastic Gradient Optimization Techniques

**Type:** Topics  
**Canonical URL:** https://scholariq.org/topics/stochastic-gradient-optimization-techniques/

## Facts

| Field | Value |
| --- | --- |
| Description | This cluster of papers focuses on the application of optimization methods in machine learning, particularly in the context of stochastic gradient descent, random projections, deep learning, convex optimization, matrix decompositions, and large-scale optimization. The papers explore various algorithms and techniques for improving the efficiency and effectiveness of machine learning models, with a specific emphasis on neural networks and generalization. |
| Domain | Physical Sciences |
| Field | Computer Science |
| OpenAlex ID | t11612 |
| Works | 11 |

## Topic papers all

- [Don't Decay the Learning Rate, Increase the Batch Size](https://scholariq.org/papers/don-t-decay-the-learning-rate-increase-the-batch-size/)
- [Don't decay the learning rate, increase the batch size](https://scholariq.org/papers/don-t-decay-the-learning-rate-increase-the-batch-size-2/)
- [Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation](https://scholariq.org/papers/secure-logistic-regression-based-on-homomorphic-encryption-design-and-evaluation/)
- [A geometric alternative to Nesterov's accelerated gradient descent](https://scholariq.org/papers/a-geometric-alternative-to-nesterov-s-accelerated-gradient-descent/)
- [Towards Pervasive and User Satisfactory CNN across GPU Microarchitectures](https://scholariq.org/papers/towards-pervasive-and-user-satisfactory-cnn-across-gpu-microarchitectures/)
- [COMB-MCM: Computing-on-Memory-Boundary NN Processor with Bipolar Bitwise Sparsity Optimization for Scalable Multi-Chiplet-Module Edge Machine Learning](https://scholariq.org/papers/comb-mcm-computing-on-memory-boundary-nn-processor-with-bipolar-bitwise-sparsity/)
- [Incremental extreme learning machine based on deep feature embedded](https://scholariq.org/papers/incremental-extreme-learning-machine-based-on-deep-feature-embedded/)
- [Federated learning with hyper-parameter optimization](https://scholariq.org/papers/federated-learning-with-hyper-parameter-optimization/)
- [Demystifying Impact of Key Hyper-Parameters in Federated Learning: A Case Study on CIFAR-10 and FashionMNIST](https://scholariq.org/papers/demystifying-impact-of-key-hyper-parameters-in-federated-learning-a-case-study/)
- [CQ-CNN: A lightweight hybrid classical–quantum convolutional neural network for Alzheimer’s disease detection using 3D structural brain MRI](https://scholariq.org/papers/cq-cnn-a-lightweight-hybrid-classical-quantum-convolutional-neural-network-for/)
- [FedEasy : Federated learning with ease](https://scholariq.org/papers/fedeasy-federated-learning-with-ease/)

## Topic primary papers

- [A geometric alternative to Nesterov's accelerated gradient descent](https://scholariq.org/papers/a-geometric-alternative-to-nesterov-s-accelerated-gradient-descent/)

---
Source: ScholarIQ — public research metadata, principally OpenAlex. See https://scholariq.org/sources/ for provenance and https://scholariq.org/methodology/ for what these figures mean.