activity
20232026
collaborators

9 papers

cs.LG2026

Compute Efficiency and Serial Runtime Tradeoffs for Stochastic Momentum Methods

Depen Morwani, Alexandru Meterez, Pranav Nair +1

Stochastic momentum methods such as heavy ball (HB), Nesterov momentum, and variants of Accelerated SGD (ASGD) [Kidambi et al., 2018] are widely used in modern training, but their…

cs.SE2026

GenAI for Systems: Recurring Challenges and Design Principles from Software to Silicon

Arya Tschand, Chenyu Wang, Zishen Wan +21

Generative AI is reshaping how computing systems are designed, optimized, and built, yet research remains fragmented across software, architecture, and chip design communities. Thi…

cs.LG2026

Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging

Alexandru Meterez, Pranav Ajit Nair, Depen Morwani +2

Large language models are increasingly trained in continual or open-ended settings, where the total training horizon is not known in advance. Despite this, most existing pretrainin…

cs.LG2025

Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling

Alexandru Meterez, Depen Morwani, Jingfeng Wu +3

Increasing the batch size during training -- a ''batch ramp'' -- is a promising strategy to accelerate large language model pretraining. While for SGD, doubling the batch size can…

cs.LG2025

A Simplified Analysis of SGD for Linear Regression with Weight Averaging

Alexandru Meterez, Depen Morwani, Costin-Andrei Oncescu +3

Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in prac…

cs.LG2025

Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining

Rosie Zhao, Alexandru Meterez, Sham Kakade +3

Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models for advanced mathematical reasoning and coding. Following the success of fr…