Statistical Learning
Smoothly Bounding User Contributions in Differential Privacy
In many applications of differential privacy, a single user might contribute more than one data point. A prominent example, which is the focus of this paper, is private machine learning, where a user often provides several points in the training data set.
Smoothly Bounding User Contributions in Differential Privacy
In many applications of differential privacy, a single user might contribute more than one data point. A prominent example, which is the focus of this paper, is private machine learning, where a user often provides several points in the training data set.
A Proof of Theorem 1 Recall that under maximum entropy RL, the Q-function is defined as Q
D.2 Additional experiment results Comparison across related baselines.
A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent
This has been highlighted perhaps most prominently in recent work on neural network models, in which the model complexity and data size increase together.
812214fb8e7066bfa6e32c626c2c688b-Paper.pdf
In this work, we argue that the order of play in strategic classification is fundamentally determined by the relative frequencies at which the decision-maker and the agents adapt to each other's actions.
main
The classical theory of reinforcement learning (RL) has focused on tabular and linear representations of value functions.