Search Results for author:
Found 10 papers, 5 papers with code
Cross-Modal Fine-Tuning: Align then Refine
Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP.
Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
Tuning hyperparameters is a crucial but arduous part of the machine learning pipeline.
Rethinking Neural Operations for Diverse Tasks
An important goal of AutoML is to automate-away the design of neural networks on new tasks in under-explored domains.
On Data Efficiency of Meta-learning
Meta-learning has enabled learning statistical models that can be quickly adapted to new prediction tasks.
Searching for Convolutions and a More Ambitious NAS
An important goal of neural architecture search (NAS) is to automate-away the design of neural networks on new tasks in under-explored domains, thus helping to democratize machine learning.
Geometry-Aware Gradient Algorithms for Neural Architecture Search
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 shared-weights, a noisy process that remains poorly understood.
On Weight-Sharing and Bilevel Optimization in Architecture Search
Weight-sharing—the simultaneous optimization of multiple neural networks using the same parameters—has emerged as a key component of state-of-the-art neural architecture search.
Exploiting Reuse in Pipeline-Aware Hyperparameter Tuning
Hyperparameter tuning of multi-stage pipelines introduces a significant computational burden.
Random Search and Reproducibility for Neural Architecture Search
Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures.
Ranked #30 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
A System for Massively Parallel Hyperparameter Tuning
Modern learning models are characterized by large hyperparameter spaces and long training times.
