4 citations · 4 across the 2 of their papers we have counts for
5 papers
On Data Efficiency of Meta-learning
Maruan Al-Shedivat, Liam Li, Eric Xing +1
Meta-learning has enabled learning statistical models that can be quickly adapted to new prediction tasks. Motivated by use-cases in personalized federated learning, we study the o…
Geometry-Aware Gradient Algorithms for Neural Architecture Search
Liam Li, Mikhail Khodak, Maria-Florina Balcan +1
Recent state-of-the-art methods for neural architecture search (NAS) exploit gradient-based optimization by relaxing the problem into continuous optimization over architectures and…
Exploiting Reuse in Pipeline-Aware Hyperparameter Tuning
Liam Li, Evan Sparks, Kevin Jamieson +1
Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden. Motivated by the observation that work can be reused across pipelines if the intermedi…
Random Search and Reproducibility for Neural Architecture Search
Liam Li, Ameet Talwalkar
Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In this wor…
A System for Massively Parallel Hyperparameter Tuning
Liam Li, Kevin Jamieson, Afshin Rostamizadeh +4
Modern learning models are characterized by large hyperparameter spaces and long training times. These properties, coupled with the rise of parallel computing and the growing deman…