Approximation Algorithms for Cascading Prediction Models
We present an approximation algorithm that takes a pool of pre-trained models as input and produces from it a cascaded model with similar accuracy but lower average-case cost. Applied to state-of-the-art ImageNet classification models, this yields up to a 2x reduction in floating point multiplications, and up to a 6x reduction in average-case memory I/O. The auto-generated cascades exhibit intuitive properties, such as using lower-resolution input for easier images and requiring higher prediction confidence when using a computationally cheaper model.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationPredictionSimilar Papers 제목 키워드 기반
Predicting Cascading Failures in Power Systems using Machine Learning
Cascading failure studies help assess and enhance the robustness of power systems against severe power outages. Onset time is a critical parameter in the analysis and management of power system stability and reliability,…
Bayesian OptimizationManagementMulti-class ClassificationA Dual Power Grid Cascading Failure Model for the Vulnerability Analysis
Considering the attacks against the power grid, one of the most effective approaches could be the attack to the transmission lines that leads to large cascading failures. Hence, the problem of locating the most critical …
Relaxation Based Modeling of GMD Induced Cascading Failures in PowerModelsGMD.jl
A major risk of geomagnetic disturbances (GMDs) is cascading failure of electrical grids. The modeling of GMD events and cascading outages in power systems is difficult, both independently and jointly, because of the man…
The Parameterized Complexity of Cascading Portfolio Scheduling
Cascading portfolio scheduling is a static algorithm selection strategy which uses a sample of test instances to compute an optimal ordering (a cascading schedule) of a portfolio of available algorithms. The algorithms …
RelationSchedulingThompson Sampling Algorithms for Cascading Bandits
Motivated by the pressing need for efficient optimization in online recommender systems, we revisit the cascading bandit model proposed by Kveton et al. (2015). While Thompson sampling (TS) algorithms have been shown to …
Efficient ExplorationMulti-Armed BanditsRecommendation SystemsThompson Sampling