111 citations · 158 across the 13 of their papers we have counts for
11 papers · 1 filter
Exponential Hardness of Reinforcement Learning with Linear Function Approximation
Daniel Kane, Sihan Liu, Shachar Lovett +3
A fundamental question in reinforcement learning theory is: suppose the optimal value functions are linear in given features, can we learn them efficiently? This problem's counterp…
Learning Hidden Markov Models Using Conditional Samples
Sham M. Kakade, Akshay Krishnamurthy, Gaurav Mahajan +1
This paper is concerned with the computational complexity of learning the Hidden Markov Model (HMM). Although HMMs are some of the most widely used tools in sequential and time ser…
Do PAC-Learners Learn the Marginal Distribution?
Max Hopkins, Daniel M. Kane, Shachar Lovett +1
The Fundamental Theorem of PAC Learning asserts that learnability of a concept class is equivalent to the of empirical error in to its mean,…
Convergence of online -means
Sanjoy Dasgupta, Gaurav Mahajan, Geelon So
We prove asymptotic convergence for a general class of -means algorithms performed over streaming data from a distribution: the centers asymptotically converge to the set of sta…
Computational-Statistical Gaps in Reinforcement Learning
Daniel Kane, Sihan Liu, Shachar Lovett +1
Reinforcement learning with function approximation has recently achieved tremendous results in applications with large state spaces. This empirical success has motivated a growing…
Learning what to remember
Robi Bhattacharjee, Gaurav Mahajan
We consider a lifelong learning scenario in which a learner faces a neverending and arbitrary stream of facts and has to decide which ones to retain in its limited memory. We intro…
Realizable Learning is All You Need
Max Hopkins, Daniel M. Kane, Shachar Lovett +1
The equivalence of realizable and agnostic learnability is a fundamental phenomenon in learning theory. With variants ranging from classical settings like PAC learning and regressi…
Bilinear Classes: A Structural Framework for Provable Generalization in RL
Simon S. Du, Sham M. Kakade, Jason D. Lee +4
This work introduces Bilinear Classes, a new structural framework, which permit generalization in reinforcement learning in a wide variety of settings through the use of function a…
Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity
Simon S. Du, Jason D. Lee, Gaurav Mahajan +1
The current paper studies the problem of agnostic -learning with function approximation in deterministic systems where the optimal -function is approximable by a function in…
Noise-tolerant, Reliable Active Classification with Comparison Queries
Max Hopkins, Daniel Kane, Shachar Lovett +1
With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in the…
On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift
Alekh Agarwal, Sham M. Kakade, Jason D. Lee +1
Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about ev…