Accepted Papers

  • Tom Zahavy, Avinatan Hassidim, Haim Kaplan and Yishay Mansour. Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies
  • Dmitry Kovalev, Samuel Horvath and Peter Richtárik. Don’t Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop
  • Philip Long and Raphael Long. On the Complexity of Proper Distribution-Free Learning of Linear Classifiers
  • Nicolò Cesa-Bianchi, Tommaso Cesari and Claire Monteleoni. Cooperative Online Learning: Keeping your Neighbors Updated
  • Jayadev Acharya and Ananda Theertha Suresh. Optimal multiclass overfitting by sequence reconstruction from Hamming queries
  • Idan Rejwan and Yishay Mansour. Top-k Combinatorial Bandits with Full-Bandit Feedback
  • Yuval Lewi, Haim Kaplan and Yishay Mansour. Thompson Sampling for Adversarial Bit Prediction
  • Sai Ganesh Nagarajan and Ioannis Panageas. On the Analysis of EM for truncated mixtures of two Gaussians
  • Galit Bary Weisberg, Amit Daniely and Shai Shalev-Shwartz. Distribution Free Learning with Local Queries
  • Mikito Nanashima. A Non-Trivial Algorithm Enumerating Relevant Features over Finite Fields
  • Abram Magner and Wojciech Szpankowski. Toward Universal Testing of Dynamic Network Models
  • Kevin Schlegel. Approximate Representer Theorems in Non-reflexive Banach Spaces
  • Naman Agarwal, Sham Kakade, Rahul Kidambi, Yin Tat Lee, Praneeth Netrapalli and Aaron Sidford. Leverage Score Sampling for Faster Accelerated Regression and ERM
  • Anupama Nandi and Raef Bassily. Privately Answering Classification Queries in the Agnostic PAC Model
  • Charles Riou and Junya Honda. Bandit Algorithms Based on Thompson Sampling for Bounded Reward Distributions
  • Mark Sellke and Sébastien Bubeck. First-Order Bayesian Regret Analysis of Thompson Sampling
  • Yossi Arjevani, Ohad Shamir and Nathan Srebro. A Tight Convergence Analysis for Stochastic Gradient Descent with Delayed Updates
  • Arun Suggala and Praneeth Netrapalli. Online Non-Convex Learning: Following the Perturbed Leader is Optimal
  • Huy Nguyen, Jonathan Ullman and Lydia Zakynthinou. Efficient Private Algorithms for Learning Large-Margin Halfspaces
  • Roi Livni and Pravesh K Kothari. On the Expressive Power of Kernel Methods and the Efficiency of Kernel Learning by Association Schemes
  • Vanja Doskoc and Timo Kötzing. Cautious Limit Learning
  • Thodoris Lykouris, Eva Tardos and Drishti Wali. Feedback graph regret bounds for Thompson Sampling and UCB
  • Robi Bhattacharjee and Sanjoy Dasgupta. What relations are reliably embeddable in Euclidean space?
  • Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor and Soumyabrata Pal. Algebraic and Analytic Approaches for Parameter Learning in Mixture Models
  • Geoffrey Wolfer. Mixing Time Estimation in Ergodic Markov Chains from a Single Trajectory with Contraction Methods
  • Xavier Fontaine, Shie Mannor and Vianney Perchet. An adaptive stochastic optimization algorithm for resource allocation
  • Holden Lee and Cyril Zhang. Robust guarantees for learning an autoregressive filter
  • Elad Hazan, Sham Kakade and Karan Singh. The Nonstochastic Control Problem
  • Cindy Trinh, Emilie Kaufmann, Claire Vernade and Richard Combes. Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling
  • Vianney Perchet. Finding Robust Nash equilibria
  • Sanjam Garg, Somesh Jha, Saeed Mahloujifar and Mohammad Mahmoody. Adversarially Robust Learning Could Leverage Computational Hardness
  • Benjamin Fish, Lev Reyzin and Benjamin Rubinstein. Sampling Without Compromising Accuracy in Adaptive Data Analysis
  • Udaya Ghai, Elad Hazan and Yoram Singer. Exponentiated Gradient Meets Gradient Descent
  • Ehsan Emamjomeh-Zadeh, David Kempe, Mohammad Mahdian and Robert Schapire. Interactive Learning of a Dynamic Structure
  • Aditya Bhaskara and Aravinda Kanchana Ruwanpathirana. Robust Algorithms for Online k-means Clustering
  • Shubhada Agrawal, Sandeep Juneja and Peter Glynn. Optimal delta correct best-arm selection for general distributions
  • Hanti Lin and Jiji Zhang. How to Tackle an Extremely Hard Learning Problem: Learning Causal Structures from Non-Experimental Data without the Faithfulness Assumption or the Like
  • Sushant Agarwal, Nivasini Ananthakrishnan, Shai Ben-David, Tosca Lechner and Ruth Urner. On Learnability with Computable Learners