Nonmyopic Multiclass Active Search for Diverse Discovery
- URL: http://arxiv.org/abs/2202.03593v1
- Date: Tue, 8 Feb 2022 01:39:02 GMT
- Title: Nonmyopic Multiclass Active Search for Diverse Discovery
- Authors: Quan Nguyen, Roman Garnett
- Abstract summary: Active search is a setting in adaptive experimental design where we aim to uncover members of rare, valuable class(es) subject to a budget constraint.
We present a novel formulation of active search with multiple target classes, characterized by a utility function that naturally induces a preference for diversity among discoveries.
- Score: 23.752202199551572
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Active search is a setting in adaptive experimental design where we aim to
uncover members of rare, valuable class(es) subject to a budget constraint. An
important consideration in this problem is diversity among the discovered
targets -- in many applications, diverse discoveries offer more insight and may
be preferable in downstream tasks. However, most existing active search
policies either assume that all targets belong to a common positive class or
encourage diversity via simple heuristics. We present a novel formulation of
active search with multiple target classes, characterized by a utility function
that naturally induces a preference for label diversity among discoveries via a
diminishing returns mechanism. We then study this problem under the Bayesian
lens and prove a hardness result for approximating the optimal policy. Finally,
we propose an efficient, nonmyopic approximation to the optimal policy and
demonstrate its superior empirical performance across a wide variety of
experimental settings, including drug discovery.
Related papers
- Objectives Are All You Need: Solving Deceptive Problems Without Explicit
Diversity Maintenance [7.3153233408665495]
We present an approach with promise to solve deceptive domains without explicit diversity maintenance.
We use lexicase selection to optimize for these objectives as it has been shown to implicitly maintain population diversity.
We find that decomposing objectives into many objectives and optimizing them outperforms MAP-Elites on the deceptive domains that we explore.
arXiv Detail & Related papers (2023-11-04T00:09:48Z) - Multi-Target Multiplicity: Flexibility and Fairness in Target
Specification under Resource Constraints [76.84999501420938]
We introduce a conceptual and computational framework for assessing how the choice of target affects individuals' outcomes.
We show that the level of multiplicity that stems from target variable choice can be greater than that stemming from nearly-optimal models of a single target.
arXiv Detail & Related papers (2023-06-23T18:57:14Z) - L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement
Learning [16.886934253882785]
We propose L-SA (Learning by adaptive Sampling and Active querying) framework that includes adaptive sampling and active querying.
In the L-SA framework, adaptive sampling dynamically samples targets with the highest increase of success rates.
It is experimentally demonstrated that the cyclic relationship between adaptive sampling and active querying effectively improves the sample richness of under-explored targets.
arXiv Detail & Related papers (2023-05-23T06:51:51Z) - A Unified Algorithm Framework for Unsupervised Discovery of Skills based
on Determinantal Point Process [53.86223883060367]
We show that diversity and coverage in unsupervised option discovery can indeed be unified under the same mathematical framework.
Our proposed algorithm, ODPP, has undergone extensive evaluation on challenging tasks created with Mujoco and Atari.
arXiv Detail & Related papers (2022-12-01T01:40:03Z) - Adaptive Identification of Populations with Treatment Benefit in
Clinical Trials: Machine Learning Challenges and Solutions [78.31410227443102]
We study the problem of adaptively identifying patient subpopulations that benefit from a given treatment during a confirmatory clinical trial.
We propose AdaGGI and AdaGCPI, two meta-algorithms for subpopulation construction.
arXiv Detail & Related papers (2022-08-11T14:27:49Z) - Biological Sequence Design with GFlowNets [75.1642973538266]
Design of de novo biological sequences with desired properties often involves an active loop with several rounds of molecule ideation and expensive wet-lab evaluations.
This makes the diversity of proposed candidates a key consideration in the ideation phase.
We propose an active learning algorithm leveraging uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candidate solutions.
arXiv Detail & Related papers (2022-03-02T15:53:38Z) - Meta Navigator: Search for a Good Adaptation Policy for Few-shot
Learning [113.05118113697111]
Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data.
Research literature on few-shot learning exhibits great diversity, while different algorithms often excel at different few-shot learning scenarios.
We present Meta Navigator, a framework that attempts to solve the limitation in few-shot learning by seeking a higher-level strategy.
arXiv Detail & Related papers (2021-09-13T07:20:01Z) - Nonmyopic Multifidelity Active Search [15.689830609697685]
We propose a model of multifidelity active search, as well as a novel, computationally efficient policy for this setting.
We evaluate the performance of our solution on real-world datasets and demonstrate significantly better performance than natural benchmarks.
arXiv Detail & Related papers (2021-06-11T12:55:51Z) - Discovering Diverse Nearly Optimal Policies withSuccessor Features [30.144946007098852]
In reinforcement learning, a set of diverse policies can be useful for exploration, transfer, hierarchy, and robustness.
We propose Diverse Successive Policies, a method for discovering policies that are diverse in the space of Successor Features.
arXiv Detail & Related papers (2021-06-01T17:56:13Z) - Simultaneous Relevance and Diversity: A New Recommendation Inference
Approach [81.44167398308979]
We propose a new approach, which extends the general collaborative filtering (CF) by introducing a new way of CF inference, negative-to-positive.
Our approach is applicable to a wide range of recommendation scenarios/use-cases at various sophistication levels.
Our analysis and experiments on public datasets and real-world production data show that our approach outperforms existing methods on relevance and diversity simultaneously.
arXiv Detail & Related papers (2020-09-27T22:20:12Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.