A fundamental shortcoming of the concept of Nash equilibrium is its
comp...
The key assumption underlying linear Markov Decision Processes (MDPs) is...
A central problem in the theory of multi-agent reinforcement learning (M...
We consider the problem of decentralized multi-agent reinforcement learn...
A foundational problem in reinforcement learning and interactive decisio...
We consider the problem of interactive decision making, encompassing
str...
Min-max optimization problems involving nonconvex-nonconcave objectives ...
Much of reinforcement learning theory is built on top of oracles that ar...
We show that computing approximate stationary Markov coarse correlated
e...
Much of modern learning theory has been split between two regimes: the
c...
Partially Observable Markov Decision Processes (POMDPs) are a natural an...
Given a real-valued hypothesis class ℋ, we investigate under what
condit...
We study fast rates of convergence in the setting of nonparametric onlin...
Recently, Daskalakis, Fishelson, and Golowich (DFG) (NeurIPS`21) showed ...
Despite rapid progress in theoretical reinforcement learning (RL) over t...
We show that Optimistic Hedge – a common variant of
multiplicative-weigh...
We consider the problem of online classification under a privacy constra...
In many machine learning applications, the training data can contain hig...
We obtain global, non-asymptotic convergence guarantees for independent
...
In this paper we prove that the sample complexity of properly learning a...
We study the question of obtaining last-iterate convergence rates for
no...
We study closure properties for the Littlestone and threshold dimensions...
The shuffled (aka anonymous) model has recently generated significant
in...
In this paper we study the smooth convex-concave saddle point problem.
S...
We study the effect of rounds of interaction on the common randomness
ge...
An exciting new development in differential privacy is the shuffled mode...
We analyze speed of convergence to global optimum for gradient descent
t...
We study the role of interaction in the Common Randomness Generation (CR...
In Theory IIb we characterize with a mix of theory and experiments the
o...
We study the sample complexity of learning neural networks, by providing...