Papers
Exploring Controllable Text Generation Techniques
Shrimai Prabhumoye, Alan W Black, Ruslan Salakhutdinov
Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies
Tom Zahavy, Avinatan Hasidim, Haim Kaplan et al.
Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling
Cindy Trinh, Emilie Kaufmann, Claire Vernade et al.
Online Non-Convex Learning: Following the Perturbed Leader is Optimal
Arun Sai Suggala, Praneeth Netrapalli
Bandit Algorithms Based on Thompson Sampling for Bounded Reward Distributions
Charles Riou, Junya Honda
Top-k Combinatorial Bandits with Full-Bandit Feedback
Idan Rejwan, Yishay Mansour
Finding Robust Nash equilibria
Vianney Perchet
Efficient Private Algorithms for Learning Large-Margin Halfspaces
Huy Lê Nguyễn, Jonathan Ullman, Lydia Zakynthinou
Privately Answering Classification Queries in the Agnostic PAC Model
Anupama Nandi, Raef Bassily
On the Analysis of EM for truncated mixtures of two Gaussians
Sai Ganesh Nagarajan, Ioannis Panageas
Toward universal testing of dynamic network models
Abram Magner, Wojciech Szpankowski
Feedback graph regret bounds for Thompson Sampling and UCB
Thodoris Lykouris, Éva Tardos, Drishti Wali
On the Complexity of Proper Distribution-Free Learning of Linear Classifiers
Philip M. Long, Raphael J. Long
Thompson Sampling for Adversarial Bit Prediction
Yuval Lewi, Haim Kaplan, Yishay Mansour
Robust guarantees for learning an autoregressive filter
Holden Lee, Cyril Zhang
Algebraic and Analytic Approaches for Parameter Learning in Mixture Models
Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor et al.
Don’t Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop
Dmitry Kovalev, Samuel Horváth, Peter Richtárik
On the Expressive Power of Kernel Methods and the Efficiency of Kernel Learning by Association Schemes
Kothari K. Pravesh, Livni Roi
The Nonstochastic Control Problem
Elad Hazan, Sham Kakade, Karan Singh
Exponentiated Gradient Meets Gradient Descent
Udaya Ghai, Elad Hazan, Yoram Singer
Adversarially Robust Learning Could Leverage Computational Hardness.
Sanjam Garg, Somesh Jha, Saeed Mahloujifar et al.