Towards Easier-to-Tune Training Algorithms: New Results from AlgoPerf
cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Code: https://github.com/KellerJordan/modded-nanogpt
Sources
- Faster Neural Network Training with Data Echoing
- Benchmarking Neural Network Training Algorithms
- The Road Less Scheduled
- DiLoCo: Distributed Low-Communication Training of Language Models
- Benchmarking Optimizers for MLPs in Tabular Deep Learning
- SNOO: Step-K Nesterov Outer Optimizer - The Surprising Effectiveness of Nesterov Momentum Applied to Pseudo-Gradients
- The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
- Optimization Benchmark for Diffusion Models on Dynamical Systems
- Benchmarking Optimizers for Large Language Model Pretraining
- A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale
- Evolution of Optimization Methods: Algorithms, Scenarios, and Evaluations
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks