
A Simple Rewardfree Approach to Constrained Reinforcement Learning
In constrained reinforcement learning (RL), a learning agent seeks to no...
read it

The Power of Exploiter: Provable MultiAgent RL in Large State Spaces
Modern reinforcement learning (RL) commonly engages practical problems w...
read it

Minimax Optimization with Smooth Algorithmic Adversaries
This paper considers minimax optimization min_x max_y f(x, y) in the cha...
read it

Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning
This paper considers batch Reinforcement Learning (RL) with general valu...
read it

SampleEfficient Learning of Stackelberg Equilibria in GeneralSum Games
Real world applications such as economics and policy making often involv...
read it

Nearoptimal Representation Learning for Linear Bandits and Linear RL
This paper studies representation learning for multitask linear bandits...
read it

A Local Convergence Theory for Mildly OverParameterized TwoLayer Neural Network
While overparameterization is widely believed to be crucial for the suc...
read it

Bellman Eluder Dimension: New Rich Classes of RL Problems, and SampleEfficient Algorithms
Finding the minimal structural assumptions that empower sampleefficient...
read it

On Function Approximation in Reinforcement Learning: Optimism in the Face of Large State Spaces
The classical theory of reinforcement learning (RL) has focused on tabul...
read it

A Sharp Analysis of Modelbased Reinforcement Learning with SelfPlay
Modelbased algorithms—algorithms that decouple learning of the model an...
read it

SampleEfficient Reinforcement Learning of Undercomplete POMDPs
Partial observability is a common challenge in many reinforcement learni...
read it

NearOptimal Reinforcement Learning with SelfPlay
This paper considers the problem of designing optimal algorithms for rei...
read it

On the Theory of Transfer Learning: The Importance of Task Diversity
We provide new statistical guarantees for transfer learning via represen...
read it

Provable MetaLearning of Linear Representations
Metalearning, or learningtolearn, seeks to design algorithms that can...
read it

Provable SelfPlay Algorithms for Competitive Reinforcement Learning
Selfplay, where the algorithm learns by playing against itself without ...
read it

RewardFree Exploration for Reinforcement Learning
Exploration is widely regarded as one of the most challenging aspects of...
read it

NearOptimal Algorithms for Minimax Optimization
This paper resolves a longstanding open question pertaining to the desig...
read it

Provably Efficient Exploration in Policy Optimization
While policybased reinforcement learning (RL) achieves tremendous succe...
read it

Provably Efficient Reinforcement Learning with Linear Function Approximation
Modern Reinforcement Learning (RL) is commonly applied to practical prob...
read it

On Gradient Descent Ascent for NonconvexConcave Minimax Problems
We consider nonconvexconcave minimax problems, _x_y∈Y f(x, y), where f ...
read it

Stochastic Gradient Descent Escapes Saddle Points Efficiently
This paper considers the perturbed stochastic gradient descent algorithm...
read it

A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm
In this note, we derive concentration inequalities for random vectors wi...
read it

Minmax Optimization: Stable Limit Points of Gradient Descent Ascent are Locally Optimal
Minmax optimization, especially in its general nonconvexnonconcave form...
read it

Sampling Can Be Faster Than Optimization
Optimization algorithms and Monte Carlo sampling algorithms have provide...
read it

Is Qlearning Provably Efficient?
Modelfree reinforcement learning (RL) algorithms, such as Qlearning, d...
read it

Stability and Convergence Tradeoff of Iterative Optimization Algorithms
The overall performance or expected excess risk of an iterative machine ...
read it

Minimizing Nonconvex Population Risk from Rough Empirical Risk
Population riskthe expectation of the loss over the sampling mechanis...
read it

Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent
Nesterov's accelerated gradient descent (AGD), an instance of the genera...
read it

Stochastic Cubic Regularization for Fast Nonconvex Optimization
This paper proposes a stochastic variant of a classic algorithmthe cu...
read it

Gradient Descent Can Take Exponential Time to Escape Saddle Points
Although gradient descent (GD) almost always escapes saddle points asymp...
read it

No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis
In this paper we develop a new framework that captures the common landsc...
read it

How to Escape Saddle Points Efficiently
This paper shows that a perturbed form of gradient descent converges to ...
read it

Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences
We provide two fundamental results on the population (infinitesample) l...
read it

Provable Efficient Online Matrix Completion via Nonconvex Stochastic Gradient Descent
Matrix completion, where we wish to recover a low rank matrix by observi...
read it

Efficient Algorithms for Largescale Generalized Eigenvector Computation and Canonical Correlation Analysis
This paper considers the problem of canonicalcorrelation analysis (CCA)...
read it

Streaming PCA: Matching Matrix Bernstein and NearOptimal Finite Sample Guarantees for Oja's Algorithm
This work provides improved guarantees for streaming principle component...
read it

Escaping From Saddle Points  Online Stochastic Gradient for Tensor Decomposition
We analyze stochastic gradient descent for optimizing nonconvex functio...
read it

Differentially Private Data Releasing for Smooth Queries with Synthetic Database Output
We consider accurately answering smooth queries while preserving differe...
read it