Stem bandit$ (all stems)

62 papers:

CASE-2015-LaskeyMMPPBKAG #2d #modelling #multi #nondeterminism

Multi-armed bandit models for 2D grasp planning with uncertainty (ML, JM, ZM, FTP, SP, JPvdB, DK, PA, KG), pp. 572–579.

ICEIS-v1-2015-BurtiniLL #multi #online

Improving Online Marketing Experiments with Drifting Multi-armed Bandits (GB, JL, RL), pp. 630–636.

ICML-2015-CarpentierV #infinity

Simple regret for infinitely many armed bandits (AC, MV), pp. 1133–1141.

ICML-2015-GajaneUC #algorithm #exponential

A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits (PG, TU, FC), pp. 218–227.

ICML-2015-HanawalSVM

Cheap Bandits (MKH, VS, MV, RM), pp. 2133–2142.

ICML-2015-KandasamySP #modelling #optimisation

High Dimensional Bayesian Optimisation and Bandits via Additive Models (KK, JGS, BP), pp. 295–304.

ICML-2015-KomiyamaHN #analysis #multi #probability #problem

Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays (JK, JH, HN), pp. 1152–1161.

ICML-2015-KvetonSWA #learning #rank

Cascading Bandits: Learning to Rank in the Cascade Model (BK, CS, ZW, AA), pp. 767–776.

ICML-2015-SwaminathanJ #feedback #learning

Counterfactual Risk Minimization: Learning from Logged Bandit Feedback (AS, TJ), pp. 814–823.

ICML-2015-SzorenyiBWH #approach #multi

Qualitative Multi-Armed Bandits: A Quantile-Based Approach (BS, RBF, PW, EH), pp. 1660–1668.

ICML-2015-WenKA #combinator #learning #performance #scalability

Efficient Learning in Large-Scale Combinatorial Semi-Bandits (ZW, BK, AA), pp. 1113–1122.

SIGIR-2015-TangJLZL #personalisation #recommendation

Personalized Recommendation via Parameter-Free Contextual Bandits (LT, YJ, LL, CZ, TL), pp. 323–332.

STOC-2014-DekelDKP

Bandits with switching costs: T2/3 regret (OD, JD, TK, YP), pp. 459–467.

CIKM-2014-NguyenL #clustering #multi

Dynamic Clustering of Contextual Multi-Armed Bandits (TTN, HWL), pp. 1959–1962.

ICML-c1-2014-ChenLL #multi #online #problem

Boosting with Online Binary Learners for the Multiclass Bandit Problem (STC, HTL, CJL), pp. 342–350.

ICML-c1-2014-CombesP #algorithm #bound

Unimodal Bandits: Regret Lower Bounds and Optimal Algorithms (RC, AP), pp. 521–529.

ICML-c1-2014-MaillardM

Latent Bandits (OAM, SM), pp. 136–144.

ICML-c1-2014-SeldinBCA #multi #predict

Prediction with Limited Advice and Multiarmed Bandits with Paid Observations (YS, PLB, KC, YAY), pp. 280–287.

ICML-c2-2014-AgarwalHKLLS #algorithm #performance

Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits (AA, DH, SK, JL, LL, RES), pp. 1638–1646.

ICML-c2-2014-AilonKJ

Reducing Dueling Bandits to Cardinal Bandits (NA, ZSK, TJ), pp. 856–864.

ICML-c2-2014-AzarLB #correlation #feedback #online #optimisation #probability

Online Stochastic Optimization under Correlated Bandit Feedback (MGA, AL, EB), pp. 1557–1565.

ICML-c2-2014-GentileLZ #clustering #online

Online Clustering of Bandits (CG, SL, GZ), pp. 757–765.

ICML-c2-2014-MaryPN #algorithm #evaluation

Improving offline evaluation of contextual bandit algorithms via bootstrapping techniques (JM, PP, ON), pp. 172–180.

ICML-c2-2014-NeufeldGSS #adaptation #monte carlo

Adaptive Monte Carlo via Bandit Allocation (JN, AG, CS, DS), pp. 1944–1952.

ICML-c2-2014-SeldinS #algorithm #probability

One Practical Algorithm for Both Stochastic and Adversarial Bandits (YS, AS), pp. 1287–1295.

ICML-c2-2014-ValkoMKK #graph

Spectral Bandits for Smooth Graph Functions (MV, RM, BK, TK), pp. 46–54.

ICML-c2-2014-ZoghiWMR #bound #problem

Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem (MZ, SW, RM, MdR), pp. 10–18.

KDD-2014-FangT #linear

Networked bandits with disjoint linear payoffs (MF, DT), pp. 1106–1115.

RecSys-2014-TangJLL #personalisation #recommendation

Ensemble contextual bandits for personalized recommendation (LT, YJ, LL, TL), pp. 73–80.

ICML-c1-2013-AbernethyAKD #learning #problem #scalability

Large-Scale Bandit Problems and KWIK Learning (JA, KA, MK, MD), pp. 588–596.

ICML-c1-2013-BubeckWV #identification #multi

Multiple Identifications in Multi-Armed Bandits (SB, TW, NV), pp. 258–265.

ICML-c1-2013-ChenWY #combinator #framework #multi

Combinatorial Multi-Armed Bandit: General Framework and Applications (WC, YW, YY), pp. 151–159.

ICML-c2-2013-UrvoyCFN

Generic Exploration and K-armed Voting Bandits (TU, FC, RF, SN), pp. 91–99.

ICML-c3-2013-AgrawalG #linear

Thompson Sampling for Contextual Bandits with Linear Payoffs (SA, NG), pp. 127–135.

ICML-c3-2013-KarninKS #multi

Almost Optimal Exploration in Multi-Armed Bandits (ZSK, TK, OS), pp. 1238–1246.

ICML-c3-2013-SzorenyiBHOJK #algorithm #distributed #probability

Gossip-based distributed stochastic bandit algorithms (BS, RBF, IH, RO, MJ, BK), pp. 19–27.

CGO-2013-EklovNBH #memory management

Bandwidth Bandit: Quantitative characterization of memory contention (DE, NN, DBS, EH), p. 10.

ICML-2012-AvnerMS #multi

Decoupling Exploration and Exploitation in Multi-Armed Bandits (OA, SM, OS), p. 145.

ICML-2012-DekelTA #adaptation #learning #online #policy

Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret (OD, AT, RA), p. 227.

ICML-2012-DesautelsKB #optimisation #process #trade-off

Parallelizing Exploration-Exploitation Tradeoffs with Gaussian Process Bandit Optimization (TD, AK, JWB), p. 109.

ICML-2012-FreitasSZ #bound #exponential #process

Exponential Regret Bounds for Gaussian Process Bandits with Deterministic Observations (NdF, AJS, MZ), p. 125.

ICML-2012-KalyanakrishnanTAS #multi #probability #set

PAC Subset Selection in Stochastic Multi-armed Bandits (SK, AT, PA, PS), p. 34.

ICML-2012-YueHG

Hierarchical Exploration for Accelerating Contextual Bandits (YY, SAH, CG), p. 128.

ICML-2011-CrammerG #adaptation #classification #feedback #multi #using

Multiclass Classification with Bandit Feedback using Adaptive Regularization (KC, CG), pp. 273–280.

ICML-2011-YueJ

Beat the Mean Bandit (YY, TJ), pp. 241–248.

ICML-2011-YuM

Unimodal Bandits (JYY, SM), pp. 41–48.

KDD-2011-ValizadeganJW #learning #multi #predict

Learning to trade off between exploration and exploitation in multiclass bandit prediction (HV, RJ, SW), pp. 204–212.

ICML-2010-Busa-FeketeK #performance #using

Fast boosting using adversarial bandits (RBF, BK), pp. 143–150.

ICML-2010-KalyanakrishnanS #multi #performance #theory and practice

Efficient Selection of Multiple Bandit Arms: Theory and Practice (SK, PS), pp. 511–518.

ICML-2010-SrinivasKKS #design #optimisation #process

Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design (NS, AK, SK, MWS), pp. 1015–1022.

ICALP-v2-2009-GuhaM #metric #multi

Multi-armed Bandits with Metric Switching Costs (SG, KM), pp. 496–507.

ICML-2009-MesmayRVP #graph #library #optimisation #performance

Bandit-based optimization on graphs with application to library performance tuning (FdM, AR, YV, MP), pp. 729–736.

ICML-2009-YueJ #information retrieval #optimisation #problem

Interactively optimizing information retrieval systems as a dueling bandits problem (YY, TJ), pp. 1201–1208.

ICML-2009-YuM #problem

Piecewise-stationary bandit problems with side observations (JYY, SM), pp. 1177–1184.

STOC-2008-KleinbergSU #metric #multi

Multi-armed bandits in metric spaces (RK, AS, EU), pp. 681–690.

ICML-2008-KakadeST #algorithm #multi #online #performance #predict

Efficient bandit algorithms for online multiclass prediction (SMK, SSS, AT), pp. 440–447.

ICML-2008-RadlinskiKJ #learning #multi #ranking

Learning diverse rankings with multi-armed bandits (FR, RK, TJ), pp. 784–791.

ICML-2007-PandeyCA #multi #problem

Multi-armed bandit problems with dependent arms (SP, DC, DA), pp. 721–728.

ICML-2006-StrehlMLH #learning #problem

Experience-efficient learning in associative bandit problems (ALS, CM, MLL, HH), pp. 889–896.

ICML-1998-Cesa-BianchiF #bound #finite #multi #problem

Finite-Time Regret Bounds for the Multiarmed Bandit Problem (NCB, PF), pp. 100–108.

ICML-1995-Duff #problem

Q-Learning for Bandit Problems (MOD), pp. 209–217.

ICML-1995-SalganicoffU #learning #multi #using

Active Exploration and Learning in real-Valued Spaces using Multi-Armed Bandit Allocation Indices (MS, LHU), pp. 480–487.