Sham M. Kakade

CoRR, 2023

Learning an Inventory Control Policy with General Inventory Arrival Dynamics.

[BibT_eX]

[DOI]

CoRR, 2023

MatFormer: Nested Transformer for Elastic Inference.

[BibT_eX]

[DOI]

CoRR, 2023

Pareto Frontiers in Neural Feature Learning: Data, Compute, Width, and Luck.

[BibT_eX]

[DOI]

CoRR, 2023

Scaling Laws for Imitation Learning in NetHack.

[BibT_eX]

[DOI]

CoRR, 2023

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning.

[BibT_eX]

[DOI]

CoRR, 2023

Learning High-Dimensional Single-Neuron ReLU Networks with Finite Samples.

[BibT_eX]

[DOI]

CoRR, 2023

Modified Gauss-Newton Algorithms under Noise.

[BibT_eX]

[DOI]

Proceedings of the IEEE Statistical Signal Processing Workshop, 2023

AdANNS: A Framework for Adaptive Semantic Search.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

On Provable Copyright Protection for Generative Models.

[BibT_eX]

[DOI]

Nikhil Vyas

Boaz Barak

Proceedings of the International Conference on Machine Learning, 2023

Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games.

[BibT_eX]

[DOI]

Dylan J. Foster

Noah Golowich

Proceedings of the International Conference on Machine Learning, 2023

The Role of Coverage in Online Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Learning Hidden Markov Models Using Conditional Samples.

[BibT_eX]

[DOI]

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Robust Aggregation for Federated Learning.

[BibT_eX]

[DOI]

Krishna Pillutla

IEEE Trans. Signal Process., 2022

Matryoshka Representations for Adaptive Deployment.

[BibT_eX]

[DOI]

William Howard-Snyder

CoRR, 2022

A Sharp Characterization of Linear Estimators for Offline Policy Evaluation.

[BibT_eX]

[DOI]

CoRR, 2022

Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Matryoshka Representation Learning.

[BibT_eX]

[DOI]

William Howard-Snyder

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Understanding Contrastive Learning Requires Incorporating Inductive Biases.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Sparsity in Partially Controllable Linear Systems.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Inductive Biases and Variable Creation in Self-Attention Mechanisms.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Multi-Stage Episodic Control for Strategic Exploration in Text Games.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Anti-Concentrated Confidence Bonuses For Scalable Exploration.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2021

On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points.

[BibT_eX]

[DOI]

J. ACM, 2021

The Statistical Complexity of Interactive Decision Making.

[BibT_eX]

[DOI]

CoRR, 2021

A Short Note on the Relationship of Information Gain and Eluder Dimension.

[BibT_eX]

[DOI]

CoRR, 2021

Koopman Spectrum Nonlinear Regulator and Provably Efficient Online Learning.

[BibT_eX]

[DOI]

CoRR, 2021

An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap.

[BibT_eX]

[DOI]

Yuanhao Wang

Ruosong Wang

CoRR, 2021

The Benefits of Implicit Regularization from SGD in Least Squares Problems.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

An Exponential Lower Bound for Linearly Realizable MDP with Constant Suboptimality Gap.

[BibT_eX]

[DOI]

Yuanhao Wang

Ruosong Wang

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Robust and differentially private mean estimation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Going Beyond Linear RL: Sample Efficient Neural Function Approximation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Gone Fishing: Neural Active Learning with Fisher Embeddings.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Instabilities of Offline RL with Pre-Trained Neural Representation.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Bilinear Classes: A Structural Framework for Provable Generalization in RL.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

How Important is the Train-Validation Split in Meta-Learning?

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

What are the Statistical Limits of Offline RL with Linear Function Approximation?

[BibT_eX]

[DOI]

Ruosong Wang

Proceedings of the 9th International Conference on Learning Representations, 2021

Optimal Regularization can Mitigate Double Descent.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Few-Shot Learning via Learning the Representation, Provably.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Benign Overfitting of Constant-Stepsize SGD for Linear Regression.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2021

2020

Stochastic Subgradient Method Converges on Tame Functions.

[BibT_eX]

[DOI]

Found. Comput. Math., 2020

PACT: Privacy-Sensitive Protocols And Mechanisms for Mobile Contact Tracing.

[BibT_eX]

[DOI]

Sudheesh Singanamalla

Jacob E. Sunshine

Stefano Tessaro

IEEE Data Eng. Bull., 2020

Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?

[BibT_eX]

[DOI]

CoRR, 2020

PACT: Privacy Sensitive Protocols and Mechanisms for Mobile Contact Tracing.

[BibT_eX]

[DOI]

Sudheesh Singanamalla

Jacob E. Sunshine

Stefano Tessaro

CoRR, 2020

Is Long Horizon RL More Difficult Than Short Horizon RL?

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Robust Meta-learning for Mixed Linear Regression with Small Batches.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Information Theoretic Regret Bounds for Online Nonlinear Control.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

The Implicit and Explicit Regularization Effects of Dropout.

[BibT_eX]

[DOI]

Colin Wei

Tengyu Ma

Proceedings of the 37th International Conference on Machine Learning, 2020

Soft Threshold Weight Reparameterization for Learnable Sparsity.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Meta-learning for Mixed Linear Regression.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Calibration, Entropy Rates, and Memory in Language Models.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Provable Representation Learning for Imitation Learning via Bi-level Optimization.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal.

[BibT_eX]

[DOI]

Alekh Agarwal

Lin F. Yang

Proceedings of the Conference on Learning Theory, 2020

Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes.

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2020

The Nonstochastic Control Problem.

[BibT_eX]

[DOI]

Elad Hazan

Karan Singh

Proceedings of the Algorithmic Learning Theory, 2020

Leverage Score Sampling for Faster Accelerated Regression and ERM.

[BibT_eX]

[DOI]

Proceedings of the Algorithmic Learning Theory, 2020

2019

Robust Aggregation for Federated Learning.

[BibT_eX]

[DOI]

Venkata Krishna Pillutla

CoRR, 2019

Optimal Estimation of Change in a Population of Parameters.

[BibT_eX]

[DOI]

Ramya Korlakai Vinayak

Weihao Kong

CoRR, 2019

On the Optimality of Sparse Model-Based Planning for Markov Decision Processes.

[BibT_eX]

[DOI]

Alekh Agarwal

Lin F. Yang

CoRR, 2019

The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure.

[BibT_eX]

[DOI]

CoRR, 2019

Stochastic Gradient Descent Escapes Saddle Points Efficiently.

[BibT_eX]

[DOI]

CoRR, 2019

A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm.

[BibT_eX]

[DOI]

CoRR, 2019

The Illusion of Change: Correcting for Biases in Change Inference for Sparse, Societal-Scale Data.

[BibT_eX]

[DOI]

Gabriel Cadamuro

Ramya Korlakai Vinayak

Joshua Blumenstock

Jacob Shapiro

Proceedings of the World Wide Web Conference, 2019

Meta-Learning with Implicit Gradients.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Coupled Recurrent Models for Polyphonic Music Composition.

[BibT_eX]

[DOI]

Proceedings of the 20th International Society for Music Information Retrieval Conference, 2019

Maximum Likelihood Estimation for Learning Populations of Parameters.

[BibT_eX]

[DOI]

Ramya Korlakai Vinayak

Weihao Kong

Gregory Valiant

Proceedings of the 36th International Conference on Machine Learning, 2019

Provably Efficient Maximum Entropy Exploration.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Online Meta-Learning.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Online Control with Adversarial Disturbances.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

Open Problem: Do Good Algorithms Necessarily Query Bad Points?

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2019

2018

Provably Correct Automatic Subdifferentiation for Qualified Programs.

[BibT_eX]

[DOI]

Jason D. Lee

CoRR, 2018

Global Convergence of Policy Gradient Methods for Linearized Control Problems.

[BibT_eX]

[DOI]

CoRR, 2018

Prediction with a short memory.

[BibT_eX]

[DOI]

Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing, 2018

A Smoother Way to Train Structured Prediction Models.

[BibT_eX]

[DOI]

Venkata Krishna Pillutla

Vincent Roulet

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Provably Correct Automatic Sub-Differentiation for Qualified Programs.

[BibT_eX]

[DOI]

Jason D. Lee

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization.

[BibT_eX]

[DOI]

Proceedings of the 2018 Information Theory and Applications Workshop, 2018

Recovering Structured Probability Matrices.

[BibT_eX]

[DOI]

Proceedings of the 9th Innovations in Theoretical Computer Science Conference, 2018

Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

Invariances and Data Augmentation for Supervised Music Transcription.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

Accelerating Stochastic Gradient Descent for Least Squares Regression.

[BibT_eX]

[DOI]

Proceedings of the Conference On Learning Theory, 2018

2017

Parallelizing Stochastic Gradient Descent for Least Squares Regression: Mini-batching, Averaging, and Model Misspecification.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2017

Accelerating Stochastic Gradient Descent.

[BibT_eX]

[DOI]

CoRR, 2017

Learning Overcomplete HMMs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Towards Generalization and Simplicity in Continuous Control.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

How to Escape Saddle Points Efficiently.

[BibT_eX]

[DOI]

Proceedings of the 34th International Conference on Machine Learning, 2017

Learning Features of Music From Scratch.

[BibT_eX]

[DOI]

John Thickstun

Proceedings of the 5th International Conference on Learning Representations, 2017

A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares).

[BibT_eX]

[DOI]

Venkata Krishna Pillutla

Aaron Sidford

Proceedings of the 37th IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science, 2017

Global Convergence of Non-Convex Gradient Descent for Computing Matrix Squareroot.

[BibT_eX]

[DOI]

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

2016

Minimal Realization Problems for Hidden Markov Models.

[BibT_eX]

[DOI]

IEEE Trans. Signal Process., 2016

Canonical Correlation Analysis for Analyzing Sequences of Medical Billing Codes.

[BibT_eX]

[DOI]

CoRR, 2016

Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging.

[BibT_eX]

[DOI]

CoRR, 2016

Matching Matrix Bernstein with Little Memory: Near-Optimal Finite Sample Guarantees for Oja's Algorithm.

[BibT_eX]

[DOI]

CoRR, 2016

Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent.

[BibT_eX]

[DOI]

Chi Jin

Praneeth Netrapalli

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis.

[BibT_eX]

[DOI]

Proceedings of the 33nd International Conference on Machine Learning, 2016

Faster Eigenvector Computation via Shift-and-Invert Preconditioning.

[BibT_eX]

[DOI]

Proceedings of the 33nd International Conference on Machine Learning, 2016

Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm.

[BibT_eX]

[DOI]

Proceedings of the 29th Conference on Learning Theory, 2016

2015

When are overcomplete topic models identifiable? uniqueness of tensor tucker decompositions with structured sparsity.

[BibT_eX]

[DOI]

Majid Janzamin

J. Mach. Learn. Res., 2015

Robust Shift-and-Invert Preconditioning: Faster and More Sample Efficient Algorithms for Eigenvector Computation.

[BibT_eX]

[DOI]

CoRR, 2015

Computing Matrix Squareroot via Non Convex Local Search.

[BibT_eX]

[DOI]

CoRR, 2015

A Spectral Algorithm for Latent Dirichlet Allocation.

[BibT_eX]

[DOI]

Algorithmica, 2015

Learning Mixtures of Gaussians in High Dimensions.

[BibT_eX]

[DOI]

Rong Ge

Qingqing Huang

Proceedings of the Forty-Seventh Annual ACM on Symposium on Theory of Computing, 2015

Super-Resolution Off the Grid.

[BibT_eX]

[DOI]

Qingqing Huang

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Convergence Rates of Active Learning for Maximum Likelihood Estimation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization.

[BibT_eX]

[DOI]

Proceedings of the 32nd International Conference on Machine Learning, 2015

A Linear Dynamical System Model for Text.

[BibT_eX]

[DOI]

David Belanger

Proceedings of the 32nd International Conference on Machine Learning, 2015

Competing with the Empirical Risk Minimizer in a Single Pass.

[BibT_eX]

[DOI]

Proceedings of The 28th Conference on Learning Theory, 2015

Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT).

[BibT_eX]

[DOI]

Proceedings of the Algorithmic Learning Theory - 26th International Conference, 2015

2014

Tensor decompositions for learning latent variable models.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2014

A tensor approach to learning mixed membership community models.

[BibT_eX]

[DOI]

Rong Ge

J. Mach. Learn. Res., 2014

Least Squares Revisited: Scalable Approaches for Multi-class Prediction.

[BibT_eX]

[DOI]

Proceedings of the 31th International Conference on Machine Learning, 2014

Minimal realization problem for Hidden Markov Models.

[BibT_eX]

[DOI]

Proceedings of the 52nd Annual Allerton Conference on Communication, 2014

2013

Stochastic Convex Optimization with Bandit Feedback.

[BibT_eX]

[DOI]

SIAM J. Optim., 2013

A risk comparison of ordinary least squares vs ridge regression.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2013

Optimal Dynamic Mechanism Design and the Virtual-Pivot Mechanism.

[BibT_eX]

[DOI]

Ilan Lobel

Hamid Nazerzadeh

Oper. Res., 2013

Learning mixtures of spherical gaussians: moment methods and spectral decompositions.

[BibT_eX]

[DOI]

Proceedings of the Innovations in Theoretical Computer Science, 2013

Learning Linear Bayesian Networks with Latent Variables.

[BibT_eX]

[DOI]

Adel Javanmard

Proceedings of the 30th International Conference on Machine Learning, 2013

A Tensor Spectral Approach to Learning Mixed Membership Community Models.

[BibT_eX]

[DOI]

Rong Ge

Proceedings of the COLT 2013, 2013

2012

Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2012

Domain Adaptation: A Small Sample Statistical Approach.

[BibT_eX]

[DOI]

Ruslan Salakhutdinov

Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

Regularization Techniques for Learning with Matrices.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2012

Random Design Analysis of Ridge Regression.

[BibT_eX]

[DOI]

Proceedings of the COLT 2012, 2012

(weak) Calibration is Computationally Hard.

[BibT_eX]

[DOI]

Elad Hazan

Proceedings of the COLT 2012, 2012

Towards Minimax Policies for Online Linear Optimization with Bandit Feedback.

[BibT_eX]

[DOI]

Sébastien Bubeck

Nicolò Cesa-Bianchi

Proceedings of the COLT 2012, 2012

A Method of Moments for Mixture Models and Hidden Markov Models.

[BibT_eX]

[DOI]

Proceedings of the COLT 2012, 2012

A spectral algorithm for learning Hidden Markov Models.

[BibT_eX]

[DOI]

J. Comput. Syst. Sci., 2012

Analysis of a randomized approximation scheme for matrix multiplication

[BibT_eX]

[DOI]

CoRR, 2012

Learning Gaussian Mixture Models: Moment Methods and Spectral Decompositions

[BibT_eX]

[DOI]

CoRR, 2012

Two SVDs Suffice: Spectral decompositions for probabilistic topic modeling and latent Dirichlet allocation

[BibT_eX]

[DOI]

CoRR, 2012

Learning High-Dimensional Mixtures of Graphical Models

[BibT_eX]

[DOI]

CoRR, 2012

Identifiability and Unmixing of Latent Parse Trees.

[BibT_eX]

[DOI]

Percy Liang

Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

Learning Mixtures of Tree Graphical Models.

[BibT_eX]

[DOI]

Furong Huang

Proceedings of the Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012

2011

Robust Matrix Decomposition With Sparse Corruptions.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Theory, 2011

Optimal dynamic mechanism design via a virtual VCG mechanism.

[BibT_eX]

[DOI]

Ilan Lobel

Hamid Nazerzadeh

SIGecom Exch., 2011

Preface.

[BibT_eX]

Ulrike von Luxburg

Proceedings of the COLT 2011, 2011

Domain Adaptation with Coupled Subspaces.

[BibT_eX]

[DOI]

John Blitzer

Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, 2011

A tail inequality for quadratic forms of subgaussian random vectors

[BibT_eX]

[DOI]

CoRR, 2011

An Analysis of Random Design Linear Regression

[BibT_eX]

[DOI]

CoRR, 2011

Domain Adaptation: Overfitting and Small Sample Statistics

[BibT_eX]

[DOI]

Ruslan Salakhutdinov

CoRR, 2011

Dimension-free tail inequalities for sums of random matrices.

[BibT_eX]

[DOI]

CoRR, 2011

Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

Spectral Methods for Learning Multivariate Latent Tree Structure.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, 2011

2010

Guest editorial: special issue on learning theory.

[BibT_eX]

[DOI]

Ping Li

Mach. Learn., 2010

Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, 2010

Robust Matrix Decomposition with Outliers

[BibT_eX]

[DOI]

CoRR, 2010

Learning from Logged Implicit Exploration Data

[BibT_eX]

[DOI]

Alexander L. Strehl

CoRR, 2010

An Optimal Dynamic Mechanism for Multi-Armed Bandit Processes

[BibT_eX]

[DOI]

Ilan Lobel

Hamid Nazerzadeh

CoRR, 2010

Learning from Logged Implicit Exploration Data.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, 2010

Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design.

[BibT_eX]

[DOI]

Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010

2009

Playing Games with Approximation Algorithms.

[BibT_eX]

[DOI]

Adam Tauman Kalai

Katrina Ligett

SIAM J. Comput., 2009

Online Markov Decision Processes.

[BibT_eX]

[DOI]

Math. Oper. Res., 2009

Gaussian Process Bandits without Regret: An Experimental Design Approach

[BibT_eX]

[DOI]

CoRR, 2009

Learning Exponential Families in High-Dimensions: Strong Convexity and Sparsity

[BibT_eX]

[DOI]

CoRR, 2009

Applications of strong convexity--strong smoothness duality to learning with matrices

[BibT_eX]

[DOI]

CoRR, 2009

The price of truthfulness for pay-per-click auctions.

[BibT_eX]

[DOI]

Nikhil R. Devanur

Proceedings of the Proceedings 10th ACM Conference on Electronic Commerce (EC-2009), 2009

Multi-Label Prediction via Compressed Sensing.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

Multi-view clustering via canonical correlation analysis.

[BibT_eX]

[DOI]

Proceedings of the 26th Annual International Conference on Machine Learning, 2009

2008

Information Consistency of Nonparametric Gaussian Process Methods.

[BibT_eX]

[DOI]

Matthias W. Seeger

IEEE Trans. Inf. Theory, 2008

Deterministic calibration and Nash equilibrium.

[BibT_eX]

[DOI]

J. Comput. Syst. Sci., 2008

Mind the Duality Gap: Logarithmic regret algorithms for online optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 21, 2008

On the Generalization Ability of Online Strongly Convex Programming Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 21, 2008

On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization.

[BibT_eX]

[DOI]

Karthik Sridharan

Proceedings of the Advances in Neural Information Processing Systems 21, 2008

Efficient bandit algorithms for online multiclass prediction.

[BibT_eX]

[DOI]

Proceedings of the Machine Learning, 2008

An Information Theoretic Framework for Multi-view Learning.

[BibT_eX]

[DOI]

Karthik Sridharan

Proceedings of the 21st Annual Conference on Learning Theory, 2008

Stochastic Linear Optimization under Bandit Feedback.

[BibT_eX]

[DOI]

Varsha Dani

Thomas P. Hayes

Proceedings of the 21st Annual Conference on Learning Theory, 2008

High-Probability Regret Bounds for Bandit Online Linear Optimization.

[BibT_eX]

[DOI]

Proceedings of the 21st Annual Conference on Learning Theory, 2008

2007

Maximum Entropy Correlated Equilibria.

[BibT_eX]

[DOI]

Luis E. Ortiz

Robert E. Schapire

Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, 2007

The Price of Bandit Information for Online Optimization.

[BibT_eX]

[DOI]

Varsha Dani

Thomas P. Hayes

Proceedings of the Advances in Neural Information Processing Systems 20, 2007

The Value of Observation for Monitoring Dynamic Systems.

[BibT_eX]

[DOI]

Proceedings of the IJCAI 2007, 2007

Leveragingarchivalvideo for building face datasets.

[BibT_eX]

[DOI]

Deva Ramanan

Simon Baker

Proceedings of the IEEE 11th International Conference on Computer Vision, 2007

Multi-view Regression Via Canonical Correlation Analysis.

[BibT_eX]

[DOI]

Proceedings of the Learning Theory, 20th Annual Conference on Learning Theory, 2007

2006

(In)Stability properties of limit order dynamics.

[BibT_eX]

[DOI]

Proceedings of the Proceedings 7th ACM Conference on Electronic Commerce (EC-2006), 2006

Calibration via Regression.

[BibT_eX]

[DOI]

Proceedings of the 2006 IEEE Information Theory Workshop, 2006

Cover trees for nearest neighbor.

[BibT_eX]

[DOI]

Alina Beygelzimer

Proceedings of the Machine Learning, 2006

2005

Planning in POMDPs Using Multiplicity Automata.

[BibT_eX]

[DOI]

Proceedings of the UAI '05, 2005

Worst-Case Bounds for Gaussian Process Models.

[BibT_eX]

[DOI]

Matthias W. Seeger

Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005

From Batch to Transductive Online Learning.

[BibT_eX]

[DOI]

Adam Kalai

Proceedings of the Advances in Neural Information Processing Systems 18 [Neural Information Processing Systems, 2005

Reinforcement Learning in POMDPs Without Resets.

[BibT_eX]

[DOI]

Proceedings of the IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, UK, July 30, 2005

Trading in Markovian Price Models.

[BibT_eX]

[DOI]

Michael J. Kearns

Proceedings of the Learning Theory, 18th Annual Conference on Learning Theory, 2005

2004

Competitive algorithms for VWAP and limit order trading.

[BibT_eX]

[DOI]

Proceedings of the Proceedings 5th ACM Conference on Electronic Commerce (EC-2004), 2004

Online Bounds for Bayesian Algorithms.

[BibT_eX]

[DOI]

Andrew Y. Ng

Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Economic Properties of Social Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Experts in a Markov Decision Process.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 17 [Neural Information Processing Systems, 2004

Graphical Economics.

[BibT_eX]

[DOI]

Michael J. Kearns

Luis E. Ortiz

Proceedings of the Learning Theory, 17th Annual Conference on Learning Theory, 2004

2003

Correlated equilibria in graphical games.

[BibT_eX]

[DOI]

Proceedings of the Proceedings 4th ACM Conference on Electronic Commerce (EC-2003), 2003

Policy Search by Dynamic Programming.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 16 [Neural Information Processing Systems, 2003

Exploration in Metric State Spaces.

[BibT_eX]

[DOI]

Michael J. Kearns

Proceedings of the Machine Learning, 2003

2002

Dopamine: generalization and bonuses.

[BibT_eX]

[DOI]

Neural Networks, 2002

Opponent interactions between serotonin and dopamine.

[BibT_eX]

[DOI]

Nathaniel D. Daw

Neural Networks, 2002

Competitive Analysis of the Explore/Exploit Tradeoff.

[BibT_eX]

Martin Zinkevich

Proceedings of the Machine Learning, 2002

An Alternate Objective Function for Markovian Fields.

[BibT_eX]

Yee Whye Teh

Sam T. Roweis

Proceedings of the Machine Learning, 2002

Approximately Optimal Approximate Reinforcement Learning.

[BibT_eX]

Proceedings of the Machine Learning, 2002

2001

A Natural Policy Gradient.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, 2001

Optimizing Average Reward Using Discounted Rewards.

[BibT_eX]

[DOI]

Proceedings of the Computational Learning Theory, 2001

2000

Dopamine Bonuses.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 13, 2000

Explaining Away in Weight Space.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 13, 2000

1999

Acquisition in Autoshaping.

[BibT_eX]

[DOI]