Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression. | 0 | 0.34 | 2022 |
Multi-Stage Episodic Control for Strategic Exploration in Text Games | 0 | 0.34 | 2022 |
Understanding Contrastive Learning Requires Incorporating Inductive Biases. | 0 | 0.34 | 2022 |
Benign Overfitting of Constant-Stepsize SGD for Linear Regression. | 0 | 0.34 | 2021 |
Bilinear Classes: A Structural Framework For Provable Generalization In Rl | 0 | 0.34 | 2021 |
Optimal Regularization Can Mitigate Double Descent | 0 | 0.34 | 2021 |
The Benefits of Implicit Regularization from SGD in Least Squares Problems. | 0 | 0.34 | 2021 |
How Important Is The Train-Validation Split In Meta-Learning? | 0 | 0.34 | 2021 |
Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning | 0 | 0.34 | 2020 |
Information Theoretic Regret Bounds for Online Nonlinear Control | 0 | 0.34 | 2020 |
Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity | 0 | 0.34 | 2020 |
Soft Threshold Weight Reparameterization for Learnable Sparsity | 0 | 0.34 | 2020 |
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs | 0 | 0.34 | 2020 |
The Implicit and Explicit Regularization Effects of Dropout | 0 | 0.34 | 2020 |
PACT: Privacy-Sensitive Protocols And Mechanisms for Mobile Contact Tracing. | 0 | 0.34 | 2020 |
Model-based reinforcement learning with a generative model is minimax optimal | 0 | 0.34 | 2020 |
The Nonstochastic Control Problem | 0 | 0.34 | 2020 |
Meta-Learning with Implicit Gradients | 4 | 0.39 | 2019 |
The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure. | 0 | 0.34 | 2019 |
Online Meta-Learning. | 0 | 0.34 | 2019 |
A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm. | 1 | 0.36 | 2019 |
The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares | 0 | 0.34 | 2019 |
Maximum Likelihood Estimation for Learning Populations of Parameters. | 0 | 0.34 | 2019 |
Stochastic subgradient method converges on tame functions. | 10 | 0.59 | 2018 |
Global Convergence of Policy Gradient Methods for Linearized Control Problems. | 7 | 0.53 | 2018 |
Provably Efficient Maximum Entropy Exploration. | 1 | 0.35 | 2018 |
Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control. | 4 | 0.39 | 2018 |
Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines. | 12 | 0.55 | 2018 |
Variance Reduction Methods for Sublinear Reinforcement Learning. | 3 | 0.40 | 2018 |
On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization | 0 | 0.34 | 2018 |
Recovering Structured Probability Matrices. | 0 | 0.34 | 2018 |
On the Insufficiency of Existing Momentum Schemes for Stochastic Optimization | 5 | 0.43 | 2018 |
Coupled Recurrent Models for Polyphonic Music Composition. | 0 | 0.34 | 2018 |
A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares). | 3 | 0.42 | 2017 |
Accelerating Stochastic Gradient Descent. | 0 | 0.34 | 2017 |
Minimal Realization Problems for Hidden Markov Models. | 0 | 0.34 | 2016 |
Parallelizing Stochastic Approximation Through Mini-Batching and Tail-Averaging. | 9 | 0.55 | 2016 |
Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis. | 8 | 0.48 | 2016 |
Robust Shift-and-Invert Preconditioning: Faster and More Sample Efficient Algorithms for Eigenvector Computation | 11 | 0.64 | 2015 |
Super-Resolution Off the Grid | 1 | 0.35 | 2015 |
Computing Matrix Squareroot via Non Convex Local Search | 3 | 0.38 | 2015 |
A Linear Dynamical System Model for Text. | 7 | 0.47 | 2015 |
Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization | 37 | 1.25 | 2015 |
Convergence Rates of Active Learning for Maximum Likelihood Estimation | 8 | 0.53 | 2015 |
Competing with the Empirical Risk Minimizer in a Single Pass. | 28 | 1.71 | 2015 |
A tensor approach to learning mixed membership community models | 41 | 1.23 | 2014 |
Random Design Analysis of Ridge Regression | 33 | 1.54 | 2014 |
Optimal Dynamic Mechanism Design and the Virtual-Pivot Mechanism. | 27 | 2.08 | 2013 |
Least Squares Revisited: Scalable Approaches for Multi-class Prediction. | 11 | 0.62 | 2013 |
When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity. | 3 | 0.40 | 2013 |