[go: up one dir, main page]

Lykouris et al., 2018 - Google Patents

Stochastic bandits robust to adversarial corruptions

Lykouris et al., 2018

View PDF
Document ID
9080912514908602727
Author
Lykouris T
Mirrokni V
Paes Leme R
Publication year
Publication venue
Proceedings of the 50th annual ACM SIGACT symposium on theory of computing

External Links

Snippet

We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm, eg, click fraud, fake reviews and email …
Continue reading at dl.acm.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06Q—DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce, e.g. shopping or e-commerce
    • G06Q30/02—Marketing, e.g. market research and analysis, surveying, promotions, advertising, buyer profiling, customer management or rewards; Price estimation or determination
    • G06Q30/0241—Advertisement
    • G06Q30/0251—Targeted advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06Q—DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management, e.g. organising, planning, scheduling or allocating time, human or machine resources; Enterprise planning; Organisational models
    • G06Q10/063—Operations research or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass
    • G06N99/005—Learning machines, i.e. computer in which a programme is changed according to experience gained by the machine itself during a complete run
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06Q—DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation, e.g. computer aided management of electronic mail or groupware; Time management, e.g. calendars, reminders, meetings or time accounting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06Q—DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation, e.g. linear programming, "travelling salesman problem" or "cutting stock problem"
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/54—Store-and-forward switching systems
    • H04L12/56—Packet switching systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06Q—DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/04—Exchange, e.g. stocks, commodities, derivatives or currency exchange
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/12—Computer systems based on biological models using genetic models
    • G06N3/126—Genetic algorithms, i.e. information processing using digital simulations of the genetic system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06Q—DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for a specific business sector, e.g. utilities or tourism
    • G06Q50/01—Social networking

Similar Documents

Publication Publication Date Title
Lykouris et al. Stochastic bandits robust to adversarial corruptions
Chen et al. Stabilizing reinforcement learning in dynamic environment with application to online recommendation
Chen et al. Combinatorial multi-armed bandit and its extension to probabilistically triggered arms
Babaioff et al. Dynamic pricing with limited supply
Wang et al. Improving regret bounds for combinatorial semi-bandits with probabilistically triggered arms and its applications
Zhou et al. Budget-constrained multi-armed bandits with multiple plays
Amin et al. Budget optimization for sponsored search: Censored learning in mdps
Peng et al. Fast swap regret minimization and applications to approximate correlated equilibria
US20150254372A1 (en) Updating features based on user actions in online systems
US20140250137A1 (en) Querying features based on user actions in online systems
Bouneffouf et al. Risk-aware recommender systems
Kanade et al. Sleeping experts and bandits with stochastic action availability and adversarial rewards
Zuo et al. Online competitive influence maximization
US20160314402A1 (en) Decision processing and information sharing in distributed computing environment
CN112292701A (en) Conducting policy search in multi-party policy interaction
US8230441B2 (en) Virtual world subgroup determination and segmentation for performance scalability
CN112639841B (en) Sampling scheme for policy searching in multiparty policy interactions
Ben-Porat et al. Learning with exposure constraints in recommendation systems
Resler et al. Adversarial online learning with noise
Wu et al. Soac: Supervised off-policy actor-critic for recommender systems
Lykouris et al. Bandits with adversarial scaling
Zhang et al. Online learning in contextual second-price pay-per-click auctions
Bastani et al. Sequential learning of product recommendations with customer disengagement
Li et al. Online pricing with limited supply and time-sensitive valuations
El Mimouni et al. Deep q-learning with whittle index for contextual restless bandits: Application to email recommender systems