COLT 2017: 30TH ANNUAL CONFERENCE ON LEARNING THEORY

A
Agarwal, Alekh	Corralling a Band of Bandit Algorithms Open Problem: First-Order Regret Bounds for Contextual Bandits
Agarwal, Arpit	Learning with Limited Rounds of Adaptivity: Coin Tossing, Multi-Armed Bandits, and Ranking from Pairwise Comparisons
Agarwal, Shivani	Learning with Limited Rounds of Adaptivity: Coin Tossing, Multi-Armed Bandits, and Ranking from Pairwise Comparisons
Agrawal, Shipra	Thompson Sampling for the MNL-Bandit
Anandkumar, Anima	Homotopy Analysis for Tensor PCA
Andoni, Alexandr	Correspondence retrieval
Arora, Sanjeev	On the Ability of Neural Nets to Express Distributions
Assadi, Sepehr	Learning with Limited Rounds of Adaptivity: Coin Tossing, Multi-Armed Bandits, and Ranking from Pairwise Comparisons
Avadhanula, Vashist	Thompson Sampling for the MNL-Bandit
Awasthi, Pranjal	Efficient PAC Learning from the Crowd
B
Bach, Francis	Stochastic Composite Least-Squares Regression with convergence rate O(1/n)
Bafna, Mitali	The Price of Selection in Differential Privacy
Balakrishnan, Sivaraman	Computationally Efficient Robust Estimation of Sparse Functionals
Balcan, Maria-Florina	Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems
Balkanski, Eric	The Sample Complexity of Optimizing a Convex Function
Blum, Avrim	Efficient PAC Learning from the Crowd Efficient Co-Training of Linear Separators under Weak Dependence
Boahen, Kwabena	Online Learning Without Prior Information (Best Student Paper Award)
Bogunovic, Ilija	Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization
Brosse, Nicolas	Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo
Brunel, Victor-Emmanuel	Rates of estimation for determinantal point processes
Bshouty, Nader	Learning Disjunctions of Predicates
C
Canonne, Clément	Testing Bayesian Networks
Carpentier, Alexandra	Two-Sample Tests for Large Random Graphs using Network Statistics
Carpentier, Alexandra	Adaptivity to Noise Parameters in Nonparametric Active Learning
Casalaina-Martin, Sebastian	Multi-Observation Elicitation
Cesa-Bianchi, Nicolò	Online Nonparametric Learning, Chaining, and the Role of Partial Feedback
Cevher, Volkan	Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization
Charikar, Moses	A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics (Best Paper Award)
Chen, Lijie	Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration Towards Instance Optimal Bounds for Best Arm Identification
Cherapanamjeri, Yeshwanth	Thresholding based Efficient Outlier Robust PCA
Cohen, Alon	Tight Bounds for Bandit Combinatorial Optimization
Cutkosky, Ashok	Online Learning Without Prior Information (Best Student Paper Award)
D
Dalalyan, Arnak	Further and stronger analogy between sampling and optimization: Langevin Monte Carlo and gradient descent
Daniely, Amit	Depth Separation for Neural Networks
Daskalakis, Constantinos	Square Hellinger Subadditivity for Bayesian Networks and its Applications to Identity Testing Ten Steps of EM Suffice for Mixtures of Two Gaussians
Deng, Yuan	Homotopy Analysis for Tensor PCA
Diakonikolas, Ilias	Testing Bayesian Networks Learning Multivariate Log-concave Distributions
Drachsler Cohen, Dana	Learning Disjunctions of Predicates
Du, Simon	Computationally Efficient Robust Estimation of Sparse Functionals
Durmus, Alain	Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo
F
Feldman, Moran	Greed Is Good: Near-Optimal Submodular Maximization via Greedy Optimization
Feldman, Vitaly	Generalization for Adaptively-chosen Estimators via Stable Median A General Characterization of the Statistical Query Complexity
Fish, Benjamin	Open Problem: Meeting Times for Learning Random Automata
Flammarion, Nicolas	Stochastic Composite Least-Squares Regression with convergence rate O(1/n)
Foster, Dylan	ZIGZAG: A new approach to adaptive online learning
Frongillo, Rafael	Memoryless Sequences for Differentiable Losses Multi-Observation Elicitation
G
Gaillard, Pierre	Online Nonparametric Learning, Chaining, and the Role of Partial Feedback
Gamarnik, David	Matrix Completion from O(n) Samples in Linear Time High-Dimensional Regression with Binary Coefficients. Estimating Squared Error and a Phase Transition.
Ge, Rong	On the Ability of Neural Nets to Express Distributions Homotopy Analysis for Tensor PCA
Gentile, Claudio	Online Nonparametric Learning, Chaining, and the Role of Partial Feedback
Gerchinovitz, Sébastien	Online Nonparametric Learning, Chaining, and the Role of Partial Feedback
Ghoshdastidar, Debarghya	Two-Sample Tests for Large Random Graphs using Network Statistics
Globerson, Amir	Effective Semisupervised Learning on Manifolds
Goel, Surbhi	Reliably Learning the ReLU in Polynomial Time
Gonen, Alon	Fast Rates for Empirical Risk Minimization of Strict Saddle Problems
Goyal, Vineet	Thompson Sampling for the MNL-Bandit
Gunasekar, Suriya	Learning Non-Discriminatory Predictors
Gupta, Anupam	Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration
Gutzeit, Maurilio	Two-Sample Tests for Large Random Graphs using Network Statistics
Gómez, Vicenç	Fast rates for online learning in Linearly Solvable Markov Decision Processes
H
Haghtalab, Nika	Efficient PAC Learning from the Crowd
Harshaw, Christopher	Greed Is Good: Near-Optimal Submodular Maximization via Greedy Optimization
Harvey, Nicholas	Nearly-tight VC-dimension bounds for neural networks
Hassidim, Avinatan	Submodular Optimization under Noise
Hazan, Tamir	Tight Bounds for Bandit Combinatorial Optimization
Helmbold, David	Surprising properties of dropout in deep networks
Hsu, Daniel	Correspondence retrieval
Hu, Bin	A Unified Analysis of Stochastic Optimization Methods Using Jump System Theory and Quadratic Constraints
Hu, Lunjia	Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes
J
Jain, Prateek	Thresholding based Efficient Outlier Robust PCA
Jamieson, Kevin	The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime
Jin, Rong	Empirical Risk Minimization for Stochastic Convex Optimization: $O(1/n)$- and $O(1/n^2)$-type of Risk Bounds
K
Kanade, Varun	Reliably Learning the ReLU in Polynomial Time
Kane, Daniel	Testing Bayesian Networks Learning Multivariate Log-concave Distributions
Kannan, Ravi	The Hidden Hubs Problem
Karbasi, Amin	Greed Is Good: Near-Optimal Submodular Maximization via Greedy Optimization
Kearns, Michael	Predicting with Distributions
Khanna, Sanjeev	Learning with Limited Rounds of Adaptivity: Coin Tossing, Multi-Armed Bandits, and Ranking from Pairwise Comparisons
Klivans, Adam	Reliably Learning the ReLU in Polynomial Time
Koren, Tomer	Bandits with Movement Costs and Adaptive Pricing Tight Bounds for Bandit Combinatorial Optimization
Kpotufe, Samory	Adaptivity to Noise Parameters in Nonparametric Active Learning
Krishnamurthy, Akshay	Open Problem: First-Order Regret Bounds for Contextual Bandits
Kwon, Joon	Sparse Stochastic Bandits
L
Langford, John	Open Problem: First-Order Regret Bounds for Contextual Bandits
Lee, Holden	On the Ability of Neural Nets to Express Distributions
Lelarge, Marc	Fundamental limits of symmetric low-rank matrix estimation
Li, Jerry	Computationally Efficient Robust Estimation of Sparse Functionals Robust Proper Learning for Mixtures of Gaussians via Systems of Polynomial Inequalities
Li, Jian	Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration Towards Instance Optimal Bounds for Best Arm Identification
Li, Quan	Matrix Completion from O(n) Samples in Linear Time
Li, Tianhong	Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes
Liang, Percy	A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics (Best Paper Award)
Liaw, Christopher	Nearly-tight VC-dimension bounds for neural networks
Livni, Roi	Effective Semisupervised Learning on Manifolds Bandits with Movement Costs and Adaptive Pricing
Locatelli, Andrea	Adaptivity to Noise Parameters in Nonparametric Active Learning
Long, Phil	Surprising properties of dropout in deep networks
Lovett, Shachar	Noisy Population Recovery from Unknown Noise
Lugosi, Gabor	An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits
Luo, Haipeng	Corralling a Band of Bandit Algorithms Open Problem: First-Order Regret Bounds for Contextual Bandits
M
Ma, Tengyu	On the Ability of Neural Nets to Express Distributions
Mannor, Shie	Ignoring Is a Bliss: Learning with Large Noise Through Reweighting-Minimization
Mansour, Yishay	Efficient PAC Learning from the Crowd Efficient Co-Training of Linear Separators under Weak Dependence Bandits with Movement Costs and Adaptive Pricing
Manurangsi, Pasin	Inapproximability of VC Dimension and Littlestone's Dimension
Maurer, Andreas	A second-order look at stability and generalization
Mehrabian, Abbas	Nearly-tight VC-dimension bounds for neural networks
Mei, Song	Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality
Miolane, Léo	Fundamental limits of symmetric low-rank matrix estimation
Misiakiewicz, Theodor	Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality
Mobahi, Hossein	Homotopy Analysis for Tensor PCA
Moitra, Ankur	Rates of estimation for determinantal point processes
Montanari, Andrea	Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality
Morgan, Tom	Multi-Observation Elicitation
Moshkovitz, Dana	Mixing Implies Lower Bounds for Space Bounded Learning
Moshkovitz, Michal	Mixing Implies Lower Bounds for Space Bounded Learning
Moulines, Eric	Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo
N
Nagarajan, Vaishnavh	Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems
Netrapalli, Praneeth	Thresholding based Efficient Outlier Robust PCA
Neu, Gergely	Fast rates for online learning in Linearly Solvable Markov Decision Processes
Neyshabur, Behnam	Corralling a Band of Bandit Algorithms
Nobel, Andrew	Memoryless Sequences for Differentiable Losses
O
Ohannessian, Mesrob I.	Learning Non-Discriminatory Predictors
Oliveira, Roberto	Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality
P
Pan, Qinxuan	Square Hellinger Subadditivity for Bayesian Networks and its Applications to Identity Testing
Perchet, Vianney	Sparse Stochastic Bandits
Pereyra, Marcelo	Sampling from a log-concave distribution with compact support with proximal Langevin Monte Carlo
Polyanskiy, Yury	Sample complexity of population recovery
Potechin, Aaron	Exact tensor completion with sum-of-squares
Q
Qiao, Mingda	Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration Towards Instance Optimal Bounds for Best Arm Identification
R
Raginsky, Maxim	Non-Convex Learning via Stochastic Gradient Langevin Dynamics: A Nonasymptotic Analysis
Rakhlin, Alexander	Non-Convex Learning via Stochastic Gradient Langevin Dynamics: A Nonasymptotic Analysis On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalities ZIGZAG: A new approach to adaptive online learning
Rantzer, Anders	A Unified Analysis of Stochastic Optimization Methods Using Jump System Theory and Quadratic Constraints
Recht, Benjamin	The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime
Reyzin, Lev	Open Problem: Meeting Times for Learning Random Automata
Rigollet, Philippe	Rates of estimation for determinantal point processes
Risteski, Andrej	On the Ability of Neural Nets to Express Distributions
Rubinstein, Aviad	Inapproximability of VC Dimension and Littlestone's Dimension
S
Scarlett, Jonathan	Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization
Schapire, Robert	Corralling a Band of Bandit Algorithms Open Problem: First-Order Regret Bounds for Contextual Bandits
Schmidt, Ludwig	Robust Proper Learning for Mixtures of Gaussians via Systems of Polynomial Inequalities
Schramm, Tselil	Fast and robust tensor decomposition with applications to dictionary learning
Seiler, Peter	A Unified Analysis of Stochastic Optimization Methods Using Jump System Theory and Quadratic Constraints
Seldin, Yevgeny	An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits
Shalev-Shwartz, Shai	Fast Rates for Empirical Risk Minimization of Strict Saddle Problems Effective Semisupervised Learning on Manifolds
Shi, Kevin	Correspondence retrieval
Simchowitz, Max	The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime
Singer, Yaron	Submodular Optimization under Noise The Sample Complexity of Optimizing a Convex Function
Singh, Aarti	Computationally Efficient Robust Estimation of Sparse Functionals
Srebro, Nathan	Learning Non-Discriminatory Predictors Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch Prox
Sridharan, Karthik	On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalities ZIGZAG: A new approach to adaptive online learning
Steinke, Thomas	Generalization for Adaptively-chosen Estimators via Stable Median
Steurer, David	Exact tensor completion with sum-of-squares Fast and robust tensor decomposition with applications to dictionary learning
Stewart, Alistair	Testing Bayesian Networks Learning Multivariate Log-concave Distributions
Sun, Xiaorui	Correspondence retrieval
Suresh, Ananda Theertha	Sample complexity of population recovery
T
Telgarsky, Matus	Non-Convex Learning via Stochastic Gradient Langevin Dynamics: A Nonasymptotic Analysis
Thaler, Justin	Reliably Learning the ReLU in Polynomial Time
Tzamos, Christos	Ten Steps of EM Suffice for Mixtures of Two Gaussians
U
Ullman, Jonathan	The Price of Selection in Differential Privacy
Urschel, John	Rates of estimation for determinantal point processes
V
Vadhan, Salil	On Learning versus Refutation
Vainsencher, Daniel	Ignoring Is a Bliss: Learning with Large Noise Through Reweighting-Minimization
Vechev, Martin	Learning Disjunctions of Predicates
Vempala, Santosh	The Hidden Hubs Problem
Vernade, Claire	Sparse Stochastic Bandits
Vitercik, Ellen	Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems
von Luxburg, Ulrike	Two-Sample Tests for Large Random Graphs using Network Statistics
W
Waggoner, Bo	Multi-Observation Elicitation
Wang, Jialei	Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch Prox
Wang, Liwei	Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes
Wang, Ruosong	Nearly Optimal Sampling Algorithms for Combinatorial Pure Exploration
Wang, Weiran	Memory and Communication Efficient Distributed Stochastic Optimization with Minibatch Prox
White, Colin	Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems
Woodworth, Blake	Learning Non-Discriminatory Predictors
Wu, Ruihan	Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes
Wu, Yihong	Sample complexity of population recovery
Wu, Zhiwei Steven	Predicting with Distributions
X
Xu, Huan	Ignoring Is a Bliss: Learning with Large Noise Through Reweighting-Minimization
Y
Yahav, Eran	Learning Disjunctions of Predicates
Yang, Tianbao	Empirical Risk Minimization for Stochastic Convex Optimization: $O(1/n)$- and $O(1/n^2)$-type of Risk Bounds
Z
Zadik, Ilias	High-Dimensional Regression with Binary Coefficients. Estimating Squared Error and a Phase Transition.
Zampetakis, Manolis	Ten Steps of EM Suffice for Mixtures of Two Gaussians
Zeevi, Assaf	Thompson Sampling for the MNL-Bandit
Zhang, Hongyi	Matrix Completion from O(n) Samples in Linear Time
Zhang, Jiapeng	Noisy Population Recovery from Unknown Noise
Zhang, Lijun	Empirical Risk Minimization for Stochastic Convex Optimization: $O(1/n)$- and $O(1/n^2)$-type of Risk Bounds
Zhang, Yuchen	A Hitting Time Analysis of Stochastic Gradient Langevin Dynamics (Best Paper Award)
Zhivotovskiy, Nikita	Optimal learning via local entropies and sample compression

Disclaimer | Powered by EasyChair Smart Program