Discovering General-Purpose Active Learning Strategies

2018-10-09 · ICLR 2019 5 · Ksenia Konyushkova, Raphael Sznitman, Pascal Fua

We propose a general-purpose approach to discovering active learning (AL) strategies from data. These strategies are transferable from one domain to another and can be used in conjunction with many machine learning models. To this end, we formalize the annotation process as a Markov decision process, design universal state and action spaces and introduce a new reward function that precisely model the AL objective of minimizing the annotation cost. We seek to find an optimal (non-myopic) AL strategy using reinforcement learning. We evaluate the learned strategies on multiple unrelated domains and show that they consistently outperform state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:1810.04114

Code (1)

ksenia-konyushkova/LAL-RL 공식 구현 tf

Tasks

Active Learning BIG-bench Machine Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Optimising Optimisers with Push GP

2019-10-02 · Michael Lones

This work uses Push GP to automatically design both local and population-based optimisers for continuous-valued problems. The optimisers are trained on a single function optimisation landscape, using random transformatio…

Evolving Continuous Optimisers from Scratch

2021-03-22 · Michael A. Lones

This work uses genetic programming to explore the space of continuous optimisers, with the goal of discovering novel ways of doing optimisation. In order to keep the search space broad, the optimisers are evolved from sc…

RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems

2026-05-11 · Joel Rorseth, Parke Godfrey, Lukasz Golab, Divesh Srivastava 외 arxiv

This paper demonstrates RUBEN, an interactive tool for discovering minimal rules to explain the outputs of retrieval-augmented large language models (LLMs) in data-driven applications. We leverage novel pruning strategie…

A Data-Centric Optimization Framework for Machine Learning

2021-10-20 · Oliver Rausch, Tal Ben-Nun, Nikoli Dryden, Andrei Ivanov 외

Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute. However, as frameworks specialize performance optimization to patterns in popular ne…

BIG-bench Machine Learning

Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science

2026-03-30 · Yipeng Yu arxiv

With the advancement of large language models (LLMs) in their knowledge base and reasoning capabilities, their interactive modalities have evolved from pure text to multimodality and further to agentic tool use. Conseque…

Question Answering