Alexandru Meterez

11 papers A* 3Journal 8
YearRankTypeTitle / Venue / Authors
2026 J jnl
Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging.
CoRR
Alexandru Meterez, Pranav Ajit Nair, Depen Morwani, Cengiz Pehlevan, Sham M. Kakade
2026 J jnl
GenAI for Systems: Recurring Challenges and Design Principles from Software to Silicon.
CoRR
Arya Tschand, Chenyu Wang, Zishen Wan, Andrew Cheng, Ioana Cristescu, Kevin He, Howard Huang, Alexander Ingare, Akseli Kangaslahti, Sara Kangaslahti, Theo Lebryk, Hongjin Lin, Jeffrey Jian Ma, Alexandru Meterez, Clara Mohri, Depen Morwani, Sunny Qin, Roy Rinberg, Paula Rodriguez Diaz, Alyssa Mia Taliotis, Pernille Undrum Fathi, Rosie Zhao, Todd Zhou, Vijay Janapa Reddi
2025 J jnl
A Simplified Analysis of SGD for Linear Regression with Weight Averaging.
CoRR
Alexandru Meterez, Depen Morwani, Costin-Andrei Oncescu, Jingfeng Wu, Cengiz Pehlevan, Sham M. Kakade
2025 J jnl
Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining.
CoRR
Rosie Zhao, Alexandru Meterez, Sham M. Kakade, Cengiz Pehlevan, Samy Jelassi, Eran Malach
2025 J jnl
Seesaw: Accelerating Training by Balancing Learning Rate and Batch Size Scheduling.
CoRR
Alexandru Meterez, Depen Morwani, Jingfeng Wu, Costin-Andrei Oncescu, Cengiz Pehlevan, Sham M. Kakade
2025 A* conf
The Optimization Landscape of SGD Across the Feature Learning Strength.
ICLR
Alexander B. Atanasov, Alexandru Meterez, James B. Simon, Cengiz Pehlevan
2024 A* conf
Super Consistency of Neural Network Landscapes and Learning Rate Transfer.
NeurIPS
Lorenzo Noci, Alexandru Meterez, Thomas Hofmann, Antonio Orvieto
2024 J jnl
The Optimization Landscape of SGD Across the Feature Learning Strength.
CoRR
Alexander B. Atanasov, Alexandru Meterez, James B. Simon, Cengiz Pehlevan
2024 A* conf
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion.
ICLR
Alexandru Meterez, Amir Joudaki, Francesco Orabona, Alexander Immer, Gunnar Rätsch, Hadi Daneshmand
2024 J jnl
Why do Learning Rates Transfer? Reconciling Optimization and Scaling Limits for Deep Learning.
CoRR
Lorenzo Noci, Alexandru Meterez, Thomas Hofmann, Antonio Orvieto
2023 J jnl
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion.
CoRR
Alexandru Meterez, Amir Joudaki, Francesco Orabona, Alexander Immer, Gunnar Rätsch, Hadi Daneshmand