Dynamic Model Selection for Prediction Under a Budget

2017-04-25 · Feng Nan, Venkatesh Saligrama

We present a dynamic model selection approach for resource-constrained prediction. Given an input instance at test-time, a gating function identifies a prediction model for the input among a collection of models. Our objective is to minimize overall average cost without sacrificing accuracy. We learn gating and prediction models on fully labeled training data by means of a bottom-up strategy. Our novel bottom-up method is a recursive scheme whereby a high-accuracy complex model is first trained. Then a low-complexity gating and prediction model are subsequently learnt to adaptively approximate the high-accuracy model in regions where low-cost models are capable of making highly accurate predictions. We pose an empirical loss minimization problem with cost constraints to jointly train gating and prediction models. On a number of benchmark datasets our method outperforms state-of-the-art achieving higher accuracy for the same cost.

📄 PDF Abstract BibTeX arXiv:1704.07505

Code (0)

등록된 구현이 없습니다.

Tasks

modelModel SelectionPrediction

Estimating Conditional Mutual Information for Dynamic Feature Selection

2023-06-05 · Soham Gadgil, Ian Covert, Su-In Lee

Dynamic feature selection, where we sequentially query features to make accurate predictions with a minimal budget, is a promising paradigm to reduce feature acquisition costs and provide transparency into a model's pred…

feature selection

LDDR: Linear-DPP-Based Dynamic-Resolution Frame Sampling for Video MLLMs

2026-05-12 · Jingfeng Chen, Jiawen Qian, Wendi Deng, Yinuo Guo 외 arxiv

Video understanding in multimodal large language models requires selecting informative frames from long, redundant videos under limited visual-token budgets. Existing methods often rely on uniform sampling, point-wise re…

Biased Pareto Optimization for Subset Selection with Dynamic Cost Constraints

2024-06-18 · Dan-Xuan Liu, Chao Qian

Subset selection with cost constraints aims to select a subset from a ground set to maximize a monotone objective function without exceeding a given budget, which has various applications such as influence maximization a…

Learning-Based Client Selection for Federated Learning Services Over Wireless Networks with Constrained Monetary Budgets

2022-08-08 · Zhipeng Cheng, Xuwei Fan, Minghui LiWang, Ning Chen 외

We investigate a data quality-aware dynamic client selection problem for multiple federated learning (FL) services in a wireless network, where each client offers dynamic datasets for the simultaneous training of multipl…

Deep Reinforcement Learning Federated Learning reinforcement-learning Reinforcement Learning (RL)

Semi-decentralized Federated Time Series Prediction with Client Availability Budgets

2025-09-03 · Yunkai Bao, Reza Safarzadeh, Xin Wang, Steve Drew arxiv

Federated learning (FL) effectively promotes collaborative training among distributed clients with privacy considerations in the Internet of Things (IoT) scenarios. Despite of data heterogeneity, FL clients may also be c…

Time Series Prediction Federated Learning