In-context learning refers to the ability of a model to condition on a p...
Given n i.i.d. samples drawn from an unknown distribution P, when is it
...
Policy gradient (PG) estimators for softmax policies are ineffective wit...
The success of gradient descent in ML and especially for learning neural...
We introduce a model for ant trail formation, building upon previous wor...
It is still common to use Q-learning and temporal difference (TD)
learni...
The FFT of three-dimensional (3D) input data is an important computation...
Given data drawn from an unknown distribution, D, to what extent is it
p...
Given the apparent difficulty of learning models that are robust to
adve...