paper-with-me

Papers

Approximation Algorithms for Cascading Prediction Models

2018-02-21 · ICML 2018 7 · Matthew Streeter

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.

📄 PDF Abstract BibTeX arXiv:1802.07697

Code (0)

등록된 구현이 없습니다.

Tasks

General ClassificationPrediction

Similar Papers 제목 키워드 기반

Predicting Cascading Failures in Power Systems using Machine Learning

2025-03-01 · Samita Rani Pani, Pallav Kumar Bera, Rajat Kanti Samal

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 Classification

A Dual Power Grid Cascading Failure Model for the Vulnerability Analysis

2024-05-18 · Tianxin Zhou, Xiang Li, Haibing Lu

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

2021-08-14 · Adam Mate, Arthur K. Barnes, Steven K. Morley, Jacob A. Friz-Trillo 외

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

2019-12-01 · NeurIPS 2019 12 · Eduard Eiben, Robert Ganian, Iyad Kanj, Stefan Szeider

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 …

RelationScheduling

Thompson Sampling Algorithms for Cascading Bandits

2018-10-02 · Zixin Zhong, Wang Chi Cheung, Vincent Y. F. Tan

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