paper-with-me

홈 › Papers

TaskSet: A Dataset of Optimization Tasks

2021-01-01 · Luke Metz, Niru Maheswaranathan, Ruoxi Sun, C. Daniel Freeman, Ben Poole, Jascha Sohl-Dickstein

We present TaskSet, a dataset of tasks for use in training and evaluating optimizers. TaskSet is unique in its size and diversity, containing over a thousand tasks ranging from image classification with fully connected or convolutional neural networks, to variational autoencoders, to non-volume preserving flows on a variety of datasets. As an example application of such a dataset we explore meta-learning an ordered list of hyperparameters to try sequentially. By learning this hyperparameter list from data generated using TaskSet we achieve large speedups in sample efficiency over random search. Next we use the diversity of the TaskSet and our method for learning hyperparameter lists to empirically explore the generalization of these lists to new optimization tasks in a variety of settings including ImageNet classification with Resnet50 and LM1B language modeling with transformers. As part of this work we have opensourced code for all tasks, as well as ~29 million training curves for these problems and the corresponding hyperparameters.

📄 PDF Abstract BibTeX

Code (1)

google-research/google-research/tree/master/task_set 공식 구현 jax

Tasks

Diversityimage-classificationImage ClassificationLanguage ModelingLanguage ModellingMeta-Learning

Similar Papers 제목 키워드 기반

Using a thousand optimization tasks to learn hyperparameter search strategies

2020-02-27 · Luke Metz, Niru Maheswaranathan, Ruoxi Sun, C. Daniel Freeman 외

We present TaskSet, a dataset of tasks for use in training and evaluating optimizers. TaskSet is unique in its size and diversity, containing over a thousand tasks ranging from image classification with fully connected o…

DiversityGeneral Classificationimage-classificationImage Classification+3

Embedding Adaptation is Still Needed for Few-Shot Learning

2021-04-15 · Sébastien M. R. Arnold, Fei Sha

Constructing new and more challenging tasksets is a fruitful methodology to analyse and understand few-shot classification methods. Unfortunately, existing approaches to building those tasksets are somewhat unsatisfactor…

ClusteringFew-Shot LearningPhilosophy

Tune My Adam, Please!

2025-08-27 · Theodoros Athanasiadis, Steven Adriaensen, Samuel Müller, Frank Hutter arxiv

The Adam optimizer remains one of the most widely used optimizers in deep learning, and effectively tuning its hyperparameters is key to optimizing performance. However, tuning can be tedious and costly. Freeze-thaw Baye…

Hyperparameter Optimization

Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization

2025-02-03 · Minttu Alakuijala, Ya Gao, Georgy Ananov, Samuel Kaski 외

As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability to learn to master multiple complex tasks through experience remains a key challenge. Current LLM agents, particularly …

Information RetrievalQuestion Answering

Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks

2023-09-21 · NeurIPS 2023 11

Learning curve extrapolation aims to predict model performance in later epochs of training, based on the performance in earlier epochs. In this work, we argue that, while the inherent uncertainty in the extrapolation of …