ALT 2018

34 papers

Minimax Rates and Efficient Algorithms for Noisy Sorting

Cheng Mao, Jonathan Weed, Philippe Rigollet

Efficient coordinate-wise leading eigenvector computation

Jialei Wang, Weiran Wang, Dan Garber, Nathan Srebro

Variance-Aware Regret Bounds for Undiscounted Reinforcement Learning in MDPs

Mohammad Sadegh Talebi, Odalric-ambrym Maillard

Sequential prediction with coded side information under logarithmic loss

Yanina Shkel, Maxim Raginsky, Sergio Verdu

The K-Nearest Neighbour UCB Algorithm for Multi-Armed Bandits with Covariates

Henry Reeve, Joe Mellor, Gavin Brown

Online Learning of Combinatorial Objects via Extended Formulation

Holakou Rahmanian, David P. Helmbold, S. V. N. Vishwanathan

Multi-task {K}ernel {L}earning Based on {P}robabilistic {L}ipschitzness

Anastasia Pentina, Shai Ben-David

Stephen Pasteris, Fabio Vitale, Claudio Gentile, Mark Herbster

Clustering Algorithms for the Centralized and Local Models

Kobbi Nissim, Uri Stemmer

Markov Decision Processes with Continuous Side Information

Aditya Modi, Nan Jiang, Satinder Singh, Ambuj Tewari

Learning under p-Tampering Attacks

Saeed Mahloujifar, Dimitrios I. Diochnos, Mohammad Mahmoody

An Adaptive Strategy for Active Learning with Smooth Decision Boundary

Andrea Locatelli, Alexandra Carpentier, Samory Kpotufe

Instrument-Armed Bandits

Nathan Kallus

Learning Decision Trees with Stochastic Linear Classifiers

Tom Jurgenson, Yishay Mansour

Minimax Optimal Bayes Mixtures for Memoryless Sources over Large Alphabets

Elias Jääsaari, Janne Leppä-aho, Tomi Silander, Teemu Roos

Dimension-free Information Concentration via Exp-Concavity

Ya-Ping Hsieh, Volkan Cevher

Smooth Sensitivity Based Approach for Differentially Private PCA

Alon Gonem, Ram Gilad-Bachrach

On the Help of Bounded Shot Verifiers, Comparators and Standardisers for Learnability in Inductive Inference

Ziyuan Gao, Sanjay Jain, Frank Stephan, Thomas Zeugmann

Corrupt Bandits for Preserving Local Privacy

Pratik Gajane, Tanguy Urvoy, Emilie Kaufmann

Robust Inference for Multiclass Classification

Uriel Feige, Yishay Mansour, Robert E. Schapire

Decision making with limited feedback

Danielle Ensign, Frielder Sorelle, Neville Scott, Scheidegger Carlos, Venkatasubramanian Suresh

Unperturbed: spectral analysis beyond Davis-Kahan

Justin Eldridge, Mikhail Belkin, Yusu Wang

A Better Resource Allocation Algorithm with Semi-Bandit Feedback

Yuval Dagan, Crammer Koby

Coordinate Descent Faceoff: Primal or Dual?

Dominik Csiba, Peter Richtarik

Ranking Median Regression: Learning to Order through Local Consensus

Stéphan Clémençon, Anna Korba, Eric Sibony

Convergence of Langevin MCMC in KL-divergence

Xiang Cheng, Peter Bartlett

Structure Learning of ${H}$-colorings

Antonio Blanca, Zongchen Chen, Daniel Stefankovic, Eric Vigoda

Bandit Regret Scaling with the Effective Loss Range

Nicolò Cesa-bianchi, Ohad Shamir

Sparsity, variance and curvature in multi-armed bandits

Sébastien Bubeck, Michael Cohen, Yuanzhi Li

Adaptive Group Testing Algorithms to Estimate the Number of Defectives

Nader H. Bshouty, Vivian E. Bshouty-Hurani, George Haddad, Thomas Hashem, Fadi Khoury

{Multi-Player Bandits Revisited}

Lilian Besson, Emilie Kaufmann

Learners that Use Little Information

Raef Bassily, Shay Moran, Ido Nachum, Jonathan Shafer, Amir Yehudayoff

Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence

Maryam Aziz, Jesse Anderton, Emilie Kaufmann, Javed Aslam

Algorithmic Learning Theory ALT 2018: Preface

Mehryar Mohri, Karthik Sridharan