FLAML: A Fast and Lightweight AutoML Library

05/04/2021

FLAML: A Fast and Lightweight AutoML Library

Chi Wang, Qingyun Wu, Markus Weimer, Erkang Zhu

Keywords:

Abstract Paper Similar Papers

Abstract: We study the problem of using low computational cost to automate the choices of learners and hyperparameters for an ad-hoc training dataset and error metric, by conducting trials of different configurations on the given training data. We investigate the joint impact of multiple factors on both trial cost and model error, and propose several design guidelines. Following them, we build a fast and lightweight library FLAML which optimizes for low computational resource in finding accurate models. FLAML integrates several simple but effective search strategies into an adaptive system. It significantly outperforms top-ranked AutoML libraries on a large open source AutoML benchmark under equal, or sometimes orders of magnitude smaller budget constraints.

The video of this talk cannot be embedded. You can watch it here:

https://slideslive.com/38952750

(Link will open in new window)

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at MLSYS 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

05/04/2021

FLAML: A Fast and Lightweight AutoML Library

Chi Wang, Qingyun Wu, Markus Weimer, Erkang Zhu

Keywords Paper

0

0

0

0

5:08

18/07/2021

Training Data Subset Selection for Regression with Controlled Generalization Error

Durga S, Rishabh Iyer, Ganesh Ramakrishnan, Abir De

Keywords Paper

, Algorithms, Online Learning, Algorithms, Supervised Learning

0

0

0

0

4:15

18/11/2020

Deep-n-cheap: An automated search framework for low complexity deep learning

Sourya Dey, Saikrishna C. Kanala, Keith M. Chugg, Peter A. Beerel

Keywords Paper

0

0

0

0

11:59

18/07/2021

Model Performance Scaling with Multiple Data Sources

Tatsunori Hashimoto

Keywords Paper

Algorithms, Supervised Learning

0

0

0

1

4:50

22/11/2021

Few-shot Action Recognition with Prototype-centered Attentive Learning

Xiatian Zhu, Antoine S Toisoul, Juan-Manuel Perez-Rua and
Li Zhang, Brais Martinez, Tao Xiang

Keywords Paper

Few-shot learning, Video recognition, Action classification, Small training data, Model pre-training, Meta-learning, Transformer, Self-attention learning, Cross-attention learning, Prototype learning, Prototype-centered learning, Hybrid-attention learning

0

0

0

0

2:22

06/12/2021

Efficient Training of Retrieval Models using Negative Cache

Erik Lindgren, Sashank Reddi, Ruiqi Guo, Sanjiv Kumar

Keywords Paper

deep learning, machine learning

0

0

0

0

10:41

25/07/2020

Automated embedding size search in deep recommender systems

Haochen Liu, Xiangyu Zhao, Chong Wang and
Xiaobing Liu, Jiliang Tang

Keywords Paper

embedding, recommender system, AutoML

0

0

0

0

16:19

19/08/2021

Cross-Domain Few-Shot Classification via Adversarial Task Augmentation

Haoqing Wang, Zhi-Hong Deng

Keywords Paper

Computer Vision, Recognition, Adversarial Machine Learning, Deep Learning

0

0

0

0

10:39

13/07/2020

AI4DL: Mining Behaviors of Deep Learning Workloads for Resource Management

Josep L. Berral, Chen Wang, Alaa Youssef

Keywords Paper

0

0

0

0

16:07

05/01/2021

Multi-Loss Weighting With Coefficient of Variations

Rick Groenendijk, Sezer Karaoglu, Theo Gevers, Thomas Mensink

Keywords Paper

0

0

0

0

4:56

04/07/2020

Few-Shot NLG with Pre-Trained Language Model

Zhiyu Chen, Harini Eavani, Wenhu Chen and
Yinyin Liu, William Yang Wang

Keywords Paper

natural generation, NLG, real-world applications, content selection

0

0

0

0

5:59

13/04/2021

Active learning with maximum margin sparse gaussian processes

Weishi Shi, Qi Yu

Keywords Paper

0

0

0

0

3:00

18/07/2021

A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning

Nikunj Saunshi, Arushi Gupta, Wei Hu

Keywords Paper

Algorithms, Multitask, Transfer, and Meta Learning

0

0

0

0

5:20

06/12/2020

Minimax Classification with 0-1 Loss and Performance Guarantees

Santiago Mazuelas, Andrea Zanoni, Aritz Pérez

Keywords Paper

0

0

0

0

3:22

06/12/2020

Auxiliary Task Reweighting for Minimum-data Learning

Baifeng Shi, Judy Hoffman, Kate Saenko and
Trevor Darrell, Huijuan Xu

Keywords Paper

0

0

0

0

3:28

02/02/2021

GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning

Krishnateja Killamsetty, Durga Sivasubramanian, Ganesh Ramakrishnan, Rishabh Iyer

Keywords Paper

0

0

0

0

19:14

18/07/2021

Meta-learning Hyperparameter Performance Prediction with Neural Processes

Ying WEI, Peilin Zhao, Junzhou Huang

Keywords Paper

Algorithms, Supervised Learning

0

0

0

0

5:07

06/12/2021

Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders

Amrutha Saseendran, Kathrin Skubch, Stefan Falkner, Margret Keuper

Keywords Paper

generative model

0

0

0

0

12:18

13/04/2021

Learn to expect the unexpected: Probably approximately correct domain generalization

Vikas Garg, Adam Tauman Kalai, Katrina Ligett, Steven Wu

Keywords Paper

0

0

0

0

3:01

18/07/2021

Examining and Combating Spurious Features under Distribution Shift

Chunting Zhou, Xuezhe Ma, Paul Michel, Graham Neubig

Keywords Paper

Deep Learning, Embedding and Representation learning

0

0

0

0

5:53

18/07/2021

Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries

Arjun Nitin Bhagoji, Daniel Cullina, Vikash Sehwag, Prateek Mittal

Keywords Paper

Algorithms, Adversarial Examples

0

0

0

0

5:10

02/02/2021

Any-Precision Deep Neural Networks

Haichao Yu, Haoxiang Li, Humphrey Shi and
Thomas S. Huang, Gang Hua

Keywords Paper

0

0

0

0

14:26

03/05/2021

Entropic gradient descent algorithms and wide flat minima

Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer and
Gabriele Perugini, Carlo Baldassi, Elizaveta Demyanenko, Riccardo Zecchina

Keywords Paper

flat minima, belief-propagation, statistical physics, entropic algorithms

0

0

0

0

5:38

03/05/2021

C-Learning: Horizon-Aware Cumulative Accessibility Estimation

Panteha Naderian, Gabriel Loaiza-Ganem, Harry Braviner and
Anthony Caterini, Jesse C Cresswell, Tong Li, Animesh Garg

Keywords Paper

reinforcement learning, goal reaching, Q-learning

0

0

0

0

4:49

06/12/2020

Bayesian Optimization for Iterative Learning

Vu Nguyen, Sebastian Schulze, Michael A Osborne

Keywords Paper

0

0

0

0

3:19

26/08/2020

Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation

Yuxuan Song, Ning Miao, Hao Zhou and
Lantao Yu, Mingxuan Wang, Lei Li

Keywords Paper

0

0

0

0

12:32

06/12/2021

Training Over-parameterized Models with Non-decomposable Objectives

Harikrishna Narasimhan, Aditya Menon

Keywords Paper

optimization, machine learning, fairness

0

0

0

0

8:28

05/01/2021

EvidentialMix: Learning With Combined Open-Set and Closed-Set Noisy Labels

Ragav Sachdeva, Filipe R. Cordeiro, Vasileios Belagiannis and
Ian Reid, Gustavo Carneiro

Keywords Paper

0

0

0

0

4:58

30/11/2020

Large-Scale Cross-Domain Few-Shot Learning

Jiechao Guan, Manli Zhang, Zhiwu Lu

Keywords Paper

0

0

0

0

7:26

19/08/2021

Fast Multi-label Learning

Xiuwen Gong, Dong Yuan, Wei Bao

Keywords Paper

Machine Learning, Multi-instance; Multi-label; Multi-view learning

0

0

0

0

15:18

04/07/2020

Active Imitation Learning with Noisy Guidance

Kianté Brantley, Hal Daumé III, Amr Sharaf

Keywords Paper

Active Learning, structured tasks, sequence tasks, Imitation algorithms

0

0

0

0

7:59

18/07/2021

Offline Meta-Reinforcement Learning with Advantage Weighting

Eric Mitchell, Rafael Rafailov, Xue Bin Peng and
Sergey Levine, Chelsea Finn

Keywords Paper

Algorithms, Multitask, Transfer, and Meta Learning

1

0

0

0

5:08

06/12/2021

Robust and Decomposable Average Precision for Image Retrieval

Elias Ramzi, Nicolas THOME, Clément Rambour and
Nicolas Audebert, Xavier Bitot

Keywords Paper

deep learning

0

0

0

0

8:13

06/12/2021

Uniform Sampling over Episode Difficulty

Sébastien Arnold, Guneet Dhillon, Avinash Ravichandran, Stefano Soatto

Keywords Paper

meta learning, few shot learning

0

0

0

0

13:08

13/04/2021

Critical parameters for scalable distributed learning with large batches and asynchronous updates

Sebastian Stich, Amirkeivan Mohtashami, Martin Jaggi

Keywords Paper

0

0

0

0

3:00

26/08/2020

Scalable Feature Selection for (Multitask) Gradient Boosted Trees

Cuize Han, Nikhil Rao, Daria Sorokina, Karthik Subbian

Keywords Paper

0

0

0

0

19:44

22/11/2021

Prototype-based Incremental Few-Shot Segmentation

Fabio Cermelli, Massimiliano Mancini, Yongqin Xian and
Zeynep Akata, Barbara Caputo

Keywords Paper

segmentation, incremental learning, continual learning, few shot learning, any shot learning, prototype, knowledge distillation

0

0

0

0

2:56

03/08/2020

Semi-bandit Optimization in the Dispersed Setting

Travis Dick, Wesley Pegden, Maria-Florina Balcan

Keywords Paper

0

0

0

0

8:04

06/12/2021

AutoBalance: Optimized Loss Functions for Imbalanced Data

Mingchen Li, Xuechen Zhang, Christos Thrampoulidis and
Jiasi Chen, Samet Oymak

Keywords Paper

optimization, machine learning, fairness

0

0

0

0

14:28

03/05/2021

CPT: Efficient Deep Neural Network Training via Cyclic Precision

Yonggan Fu, Han Guo, Meng Li and
Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin

Keywords Paper

low precision training, Efficient training

0

0

0

0

8:55