activity
20242026
collaborators

7 papers

cs.CL2026

AdaBoN: Adaptive Best-of-N Alignment

Vinod Raman, Hilal Asi, Satyen Kale

Recent advances in test-time alignment methods, such as Best-of-N sampling, offer a simple and effective way to steer language models (LMs) toward preferred behaviors using reward…

cs.LG2026

Faster Rates For Federated Variational Inequalities

Guanghui Wang, Satyen Kale

In this paper, we study federated optimization for solving stochastic variational inequalities (VIs), a problem that has attracted growing attention in recent years. Despite substa…

cs.LG2025

Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and Acceleration

Ahmed Khaled, Satyen Kale, Arthur Douillard +3

Modern machine learning often requires training with large batch size, distributed data, and massively parallel compute hardware (like mobile and other edge devices or distributed…

cs.CL2025

Eager Updates For Overlapped Communication and Computation in DiLoCo

Satyen Kale, Arthur Douillard, Yanislav Donchev

Distributed optimization methods such as DiLoCo have been shown to be effective in training very large models across multiple distributed workers, such as datacenters. These method…

cs.CL2025

Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch

Arthur Douillard, Yanislav Donchev, Keith Rush +11

Training of large language models (LLMs) is typically distributed across a large number of accelerators to reduce training time. Since internal states and parameter gradients need…

cs.CL2024

Efficient Stagewise Pretraining via Progressive Subnetworks

Abhishek Panigrahi, Nikunj Saunshi, Kaifeng Lyu +4

Recent developments in large language models have sparked interest in efficient pretraining methods. Stagewise training approaches to improve efficiency, like gradual stacking and…