9.4k citations · 16.5k across the 107 of their papers we have counts for
12 papers · 2 filters
Squirrel: A Switching Hyperparameter Optimizer
Noor Awad, Gresa Shala, Difan Deng +9
In this short note, we describe our submission to the NeurIPS 2020 BBO challenge. Motivated by the fact that different optimizers work well on different problems, our approach swit…
Convergence Analysis of Homotopy-SGD for non-convex optimization
Matilde Gargiani, Andrea Zanelli, Quoc Tran-Dinh +2
First-order stochastic methods for solving large-scale non-convex optimization problems are widely used in many big-data applications, e.g. training deep neural networks as well as…
Hyperparameter Transfer Across Developer Adjustments
Danny Stoll, Jörg K. H. Franke, Diane Wagner +2
After developer adjustments to a machine learning (ML) algorithm, how can the results of an old hyperparameter optimization (HPO) automatically be used to speedup a new HPO? This q…
Smooth Variational Graph Embeddings for Efficient Neural Architecture Search
Jovita Lukasik, David Friede, Arber Zela +2
Neural architecture search (NAS) has recently been addressed from various directions, including discrete, sampling-based methods and efficient differentiable approaches. While the…
Sample-Efficient Automated Deep Reinforcement Learning
Jörg K. H. Franke, Gregor Köhler, André Biedenkapp +1
Despite significant progress in challenging problems across various domains, applying state-of-the-art deep reinforcement learning (RL) algorithms remains challenging due to their…
Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks
Arber Zela, Julien Siems, Lucas Zimmer +3
The most significant barrier to the advancement of Neural Architecture Search (NAS) is its demand for large computational resources, which hinders scientifically sound empirical ev…